NikolayKozloff

500 models • 1 total models in database
Sort by:

Meta-Llama-3-8B-Instruct-bf16-correct-pre-tokenizer-and-EOS-token-Q8_0-Q6_k-Q4_K_M-GGUF

NaNK
2,259
9

jais-13b-chat-Q4_K_M-GGUF

NaNK
llama-cpp
933
1

DeepSeek-R1-Distill-Qwen-14B-Q4_K_M-GGUF

NaNK
llama-cpp
656
1

UserLM-8b-Q8_0-GGUF

NaNK
llama-cpp
542
3

OpenReasoning-Nemotron-14B-Q4_K_M-GGUF

NikolayKozloff/OpenReasoning-Nemotron-14B-Q4KM-GGUF This model was converted to GGUF format from `nvidia/OpenReasoning-Nemotron-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
347
1

gpt-oss-20b-uncensored-bf16-Q4_K_M-GGUF

NikolayKozloff/gpt-oss-20b-uncensored-bf16-Q4KM-GGUF This model was converted to GGUF format from `huizimao/gpt-oss-20b-uncensored-bf16` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
269
2

Gpt Oss 6.0b Specialized All Pruned Moe Only 7 Experts Q8 0 GGUF

NikolayKozloff/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-Q80-GGUF This model was converted to GGUF format from `AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

NaNK
llama-cpp
217
5

Qwen2-7B-Instruct-Q4_K_M-GGUF

NaNK
llama-cpp
178
5

DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-Q8_0-GGUF

NaNK
llama-cpp
153
1

YanoljaNEXT-Rosetta-12B-2510-Q6_K-GGUF

NaNK
llama-cpp
140
1

gpt-oss-20b-uncensored-bf16-Q2_K-GGUF

NikolayKozloff/gpt-oss-20b-uncensored-bf16-Q2K-GGUF This model was converted to GGUF format from `huizimao/gpt-oss-20b-uncensored-bf16` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
122
1

granite-4.0-1b-Q8_0-GGUF

NikolayKozloff/granite-4.0-1b-Q80-GGUF This model was converted to GGUF format from `ibm-granite/granite-4.0-1b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
104
1

granite-4.0-h-1b-Q8_0-GGUF

NikolayKozloff/granite-4.0-h-1b-Q80-GGUF This model was converted to GGUF format from `ibm-granite/granite-4.0-h-1b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
90
1

falcon-7b-GGUF

NaNK
88
15

SambaLingo-Russian-Chat-GGUF

84
6

YandexGPT-5-Lite-8B-instruct-Q8_0-GGUF

NaNK
llama-cpp
81
3

AI21-Jamba-Reasoning-3B-Q8_0-GGUF

NikolayKozloff/AI21-Jamba-Reasoning-3B-Q80-GGUF This model was converted to GGUF format from `ai21labs/AI21-Jamba-Reasoning-3B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
79
2

granite-4.0-350m-Q8_0-GGUF

NikolayKozloff/granite-4.0-350m-Q80-GGUF This model was converted to GGUF format from `ibm-granite/granite-4.0-350m` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

llama-cpp
76
1

Dans-PersonalityEngine-V1.3.0-12b-Q5_K_S-GGUF

NikolayKozloff/Dans-PersonalityEngine-V1.3.0-12b-Q5KS-GGUF This model was converted to GGUF format from `PocketDoc/Dans-PersonalityEngine-V1.3.0-12b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
74
1

Qwen3-8B-Q8_0-GGUF

NaNK
llama-cpp
70
1

Llama-3.1-8B-Instruct-abliterated_via_adapter-Q8_0-GGUF

NaNK
llama-cpp
64
2

YanoljaNEXT-Rosetta-12B-2510-Q4_K_M-GGUF

NaNK
llama-cpp
64
1

Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF

NaNK
llama3
63
6

csmpt7b-Czech-GGUF

NaNK
llama-cpp
60
4

YanoljaNEXT-Rosetta-12B-2510-Q5_K_M-GGUF

NaNK
llama-cpp
59
1

gemma-2-27b-Q3_K_S-GGUF

NaNK
llama-cpp
58
1

granite-4.0-h-350m-Q8_0-GGUF

NikolayKozloff/granite-4.0-h-350m-Q80-GGUF This model was converted to GGUF format from `ibm-granite/granite-4.0-h-350m` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

llama-cpp
57
1

mGPT-1.3B-georgian-GGUF

NaNK
llama-cpp
56
1

Qwen2-7B-Q4_K_M-GGUF

NaNK
llama-cpp
54
1

aya-expanse-8b-Q8_0-GGUF

NikolayKozloff/aya-expanse-8b-Q80-GGUF This model was converted to GGUF format from `CohereForAI/aya-expanse-8b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
54
1

madlad400-10b-mt-Q8_0-GGUF

NaNK
llama-cpp
52
3

DeepSeek-R1-Distill-Qwen-1.5B-Q8_0-GGUF

NaNK
llama-cpp
52
1

LFM2-8B-A1B-Q8_0-GGUF

NaNK
llama-cpp
51
1

MiniCPM4.1-8B-Q8_0-GGUF

NikolayKozloff/MiniCPM4.1-8B-Q80-GGUF This model was converted to GGUF format from `openbmb/MiniCPM4.1-8B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
50
3

aya-23-8B-q4_0-q5_0-GGUF

NaNK
50
1

DeepSeek-R1-Distill-Qwen-14B-Q5_K_M-GGUF

NaNK
llama-cpp
49
2

Mistral-Nemo-Instruct-2407-Q8_0-GGUF

NaNK
llama-cpp
48
1

YuLan-Mini-Q8_0-GGUF

llama-cpp
47
1

gemma-3-1b-it-Q8_0-GGUF

NaNK
llama-cpp
47
1

Hermes-4-14B-Q4_K_M-GGUF

NikolayKozloff/Hermes-4-14B-Q4KM-GGUF This model was converted to GGUF format from `NousResearch/Hermes-4-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
47
1

gemma-3-270m-Q8_0-GGUF

NikolayKozloff/gemma-3-270m-Q80-GGUF This model was converted to GGUF format from `google/gemma-3-270m` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

llama-cpp
46
2

GigaChat-20B-A3B-instruct-Q4_0-GGUF

NikolayKozloff/GigaChat-20B-A3B-instruct-Q40-GGUF This model was converted to GGUF format from `ai-sage/GigaChat-20B-A3B-instruct` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
45
2

Phi-SoSerious-Mini-V1-Q8_0-Q6_K-Q5_K_M-Q4_0-GGUF

43
2

medgemma-4b-it-Q8_0-GGUF

NikolayKozloff/medgemma-4b-it-Q80-GGUF This model was converted to GGUF format from `google/medgemma-4b-it` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
38
3

gemma-portuguese-luana-2b-GGUF

NaNK
llama-cpp
38
2

saiga_nemo_12b-Q5_K_M-GGUF

NaNK
llama-cpp
37
1

JanusCoder-8B-Q8_0-GGUF

NikolayKozloff/JanusCoder-8B-Q80-GGUF This model was converted to GGUF format from `internlm/JanusCoder-8B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
37
1

ERNIE-4.5-21B-A3B-Thinking-Q3_K_M-GGUF

NikolayKozloff/ERNIE-4.5-21B-A3B-Thinking-Q3KM-GGUF This model was converted to GGUF format from `baidu/ERNIE-4.5-21B-A3B-Thinking` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
36
1

tora-code-13b-v1.0

NaNK
36
0

pip-code-bandit-Q8_0-GGUF

codeLLAMA modified archi
35
4

Vikhr-Llama-3.2-1B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
35
1

gemma-2-2b-it-Q8_0-GGUF

NaNK
llama-cpp
34
1

JanusCoder-14B-Q5_K_M-GGUF

NikolayKozloff/JanusCoder-14B-Q5KM-GGUF This model was converted to GGUF format from `internlm/JanusCoder-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
34
1

JanusCoder-14B-Q4_K_S-GGUF

NaNK
llama-cpp
33
1

suzume-llama-3-8B-multilingual-Q6_K-GGUF

NaNK
llama-cpp
32
2

Hunyuan-MT-Chimera-7B-Q8_0-GGUF

NikolayKozloff/Hunyuan-MT-Chimera-7B-Q80-GGUF This model was converted to GGUF format from `tencent/Hunyuan-MT-Chimera-7B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
31
3

Qwen2-7B-Q6_K-GGUF

NaNK
llama-cpp
31
1

Hermes-4-14B-Q5_K_M-GGUF

NikolayKozloff/Hermes-4-14B-Q5KM-GGUF This model was converted to GGUF format from `NousResearch/Hermes-4-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
31
1

DeepSeek-Prover-V2-7B-Q8_0-GGUF

NikolayKozloff/DeepSeek-Prover-V2-7B-Q80-GGUF This model was converted to GGUF format from `deepseek-ai/DeepSeek-Prover-V2-7B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
30
3

Czech-GPT-2-XL-133k-GGUF

llama-cpp
30
2

madlad400-3b-mt-Q8_0-GGUF

NaNK
llama-cpp
30
1

amoral-gemma3-4B-Q8_0-GGUF

NaNK
llama-cpp
30
1

pip-library-etl-1.3b-Q8_0-GGUF

NaNK
codeLLAMA modified archi
29
2

Replete-Coder-Llama3-8B-Q5_0-GGUF

NaNK
29
1

Gemma-2-9B-It-SPPO-Iter3-Q5_0-GGUF

NaNK
llama-cpp
29
1

GigaChat-20B-A3B-instruct-Q3_K_M-GGUF

NaNK
llama-cpp
29
1

gemma-3-12b-it-Q5_K_M-GGUF

NaNK
llama-cpp
29
1

JanusCoder-14B-Q5_K_S-GGUF

NikolayKozloff/JanusCoder-14B-Q5KS-GGUF This model was converted to GGUF format from `internlm/JanusCoder-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
29
1

tora-code-7b-v1.0

NaNK
29
0

mGPT-1.3B-mari-GGUF

NaNK
llama-cpp
28
1

Qwen2-Math-7B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
28
1

salt-asr_wav-uni_1_tts_wav-uni_1-12k-Q8_0-GGUF

llama-cpp
28
1

gemma-3-12b-it-Q6_K-GGUF

NaNK
llama-cpp
28
1

Llama-3-8B-Instruct-Coder-Q8_0-GGUF

NaNK
llama
27
5

granite-3b-code-instruct-Q8_0-GGUF

NaNK
llama-cpp
27
2

Tesser-Llama-3-Ko-8B-Q4_0-GGUF

NaNK
llama-cpp
27
1

GemmaCoder3-12B-Q5_K_M-GGUF

NaNK
llama-cpp
27
1

Qwen2-7B-Q8_0-GGUF

NaNK
llama-cpp
26
2

PLLuM-12B-instruct-Q5_K_M-GGUF

NaNK
llama-cpp
26
2

Qwen2-7B-Instruct-Q4_0-GGUF

NaNK
llama-cpp
26
1

Qwen2-7B-Instruct-deccp-Q8_0-GGUF

NaNK
llama-cpp
26
1

Replete-Coder-Qwen2-1.5b-Q4_0-GGUF

NaNK
26
1

Gemma-2-9B-It-SPPO-Iter3-Q4_K_S-GGUF

NaNK
llama-cpp
26
1

gemma-2-2b-jpn-it-Q8_0-GGUF

NaNK
llama-cpp
26
1

DeepSeek-R1-Distill-Llama-8B-Q8_0-GGUF

NaNK
llama-cpp
26
1

DeepSeek-R1-Distill-Qwen-7B-Q8_0-GGUF

NaNK
llama-cpp
26
1

Vikhr-Gemma-2B-instruct-Q8_0-GGUF

NaNK
llama-cpp
25
2

Llama-3-8B-Swedish-Norwegian-Danish-checkpoint-16000-11_6_2024-Q8_0-GGUF

NaNK
llama
25
1

EuroLLM-1.7B-Q8_0-GGUF

NaNK
llama-cpp
25
1

LFM2-2.6B-Q8_0-GGUF

NikolayKozloff/LFM2-2.6B-Q80-GGUF This model was converted to GGUF format from `LiquidAI/LFM2-2.6B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
25
1

SeaPhi3-mini-Q6_K-GGUF

llama-cpp
24
1

Gromenauer-7B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
24
1

Viking-7B-Q5_K_M-GGUF

NaNK
llama-cpp
24
1

deepthought-8b-llama-v0.01-alpha-Q8_0-GGUF

NaNK
llama-cpp
24
1

granite-20b-code-instruct-Q4_0-GGUF

NaNK
llama-cpp
23
2

Qwen2-7B-Q5_K_S-GGUF

NaNK
llama-cpp
23
1

Qwen2-7B-Q4_0-GGUF

NaNK
llama-cpp
23
1

Replete-Coder-Llama3-8B-Q4_0-GGUF

NaNK
23
1

Phi-3-mini-4k-instruct-sq-LORA-F32-GGUF

llama-cpp
23
1

Dolphin3.0-Qwen2.5-3b-Q8_0-GGUF

NaNK
llama-cpp
23
1

JanusCoder-14B-Q4_K_M-GGUF

NikolayKozloff/JanusCoder-14B-Q4KM-GGUF This model was converted to GGUF format from `internlm/JanusCoder-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
23
1

kappa-3-phi-abliterated-Q8_0-GGUF

llama-cpp
22
13

Qwen2-7B-Q5_K_M-GGUF

NaNK
llama-cpp
22
2

Mistral-portuguese-luana-7b-Mathematics-GGUF

NaNK
llama-cpp
22
1

britllm-3b-v0.1-Q8_0-GGUF

NaNK
llama-cpp
22
1

RoLlama3-8b-Instruct-Q8_0-GGUF

NaNK
llama-cpp
22
1

Gemma-2-9B-It-SPPO-Iter3-Q5_K_S-GGUF

NaNK
llama-cpp
22
1

madlad400-10b-mt-Q6_K-GGUF

NaNK
llama-cpp
22
1

WizardLM-2-7B-abliterated-Q4_0-GGUF

NaNK
llama-cpp
21
2

Mistral-Small-24B-Instruct-2501-Q2_K-GGUF

NikolayKozloff/Mistral-Small-24B-Instruct-2501-Q2K-GGUF This model was converted to GGUF format from `mistralai/Mistral-Small-24B-Instruct-2501` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
21
2

Llama-portuguese-13b-Luana-v0.2-GGUF

NaNK
llama-cpp
21
1

Falcon2-5.5B-Dutch-Q4_0-GGUF

NaNK
llama-cpp
21
1

Viking-7B-Q6_K-GGUF

NaNK
llama-cpp
21
1

Gemma-2-9B-It-SPPO-Iter3-IQ4_NL-GGUF

NaNK
llama-cpp
21
1

Gemma-2-9B-It-SPPO-Iter3-Q4_0-GGUF

NaNK
llama-cpp
21
1

SauerkrautLM-Nemo-12b-Instruct-Q5_K_S-GGUF

NaNK
llama-cpp
21
1

ghost-8b-beta-1608-Q8_0-GGUF

NaNK
llama
21
1

jais-13b-chat-Q2_K-GGUF

NaNK
llama-cpp
21
1

DeepSeek-R1-Distill-Qwen-14B-Q5_K_S-GGUF

NaNK
llama-cpp
21
1

amoral-gemma3-12B-Q5_K_M-GGUF

NaNK
llama-cpp
21
1

Llama-2-7b-Ukrainian-Q8_0-GGUF

NaNK
llama-cpp
20
3

LLaMA-Mesh-Q8_0-GGUF

llama-cpp
20
3

Gemma-2-9B-It-SPPO-Iter3-Q8_0-GGUF

NaNK
llama-cpp
20
2

Falcon2-5.5B-Italian-Q8_0-GGUF

NaNK
llama-cpp
20
1

EuroLLM-9B-Q8_0-GGUF

NaNK
llama-cpp
20
1

cogito-v1-preview-llama-8B-Q8_0-GGUF

NaNK
llama-cpp
20
1

Qwen3-14B-Q4_K_M-GGUF

NaNK
llama-cpp
20
1

Hunyuan-0.5B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
20
1

SauerkrautLM-7b-v1-mistral

NaNK
20
0

Llama-2-13b-Romanian-GGUF

NaNK
19
3

SauerkrautLM-Qwen-32b-Q3_K_S-GGUF

NaNK
llama-cpp
19
3

Yi-1.5-6B-Chat-Q4_K_M-GGUF

NaNK
llama-cpp
19
3

Qwen3-1.7B-abliterated-Q8_0-GGUF

NaNK
llama-cpp
19
2

mGPT-1.3B-tajik-GGUF

NaNK
llama-cpp
19
1

Qwen2-7B-Q4_K_S-GGUF

NaNK
llama-cpp
19
1

Replete-Coder-Qwen2-1.5b-Q5_0-GGUF

NaNK
19
1

Llasa-3B-Q8_0-GGUF

NaNK
llama-cpp
19
1

granite-3.2-8b-instruct-preview-Q8_0-GGUF

NaNK
llama-cpp
19
1

reka-flash-3-Q3_K_S-GGUF

NaNK
llama-cpp
19
1

cogito-v1-preview-qwen-14B-Q4_K_M-GGUF

NaNK
llama-cpp
19
1

NextCoder-14B-Q4_K_S-GGUF

NikolayKozloff/NextCoder-14B-Q4KS-GGUF This model was converted to GGUF format from `microsoft/NextCoder-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
19
1

YanoljaNEXT-Rosetta-20B-Q2_K-GGUF

NikolayKozloff/YanoljaNEXT-Rosetta-20B-Q2K-GGUF This model was converted to GGUF format from `yanolja/YanoljaNEXT-Rosetta-20B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
19
1

Llama-3-8B-Swedish-Norwegian-Danish-Q8_0-GGUF

NaNK
llama
18
3

DeepSeek-R1-Distill-Qwen-7B-Multilingual-Q8_0-GGUF

NaNK
llama-cpp
18
3

mGPT-1.3B-armenian-GGUF

NaNK
llama-cpp
18
2

EVA-GPT-German-Q6_K-GGUF

18
2

magnum-12b-v2.5-kto-Q5_K_M-GGUF

NaNK
llama-cpp
18
2

Hebrew-Gemma-11B-V2-Q6_K-GGUF

NaNK
llama-cpp
18
1

Phi-3-mini-4k-instruct-dansk-Q8_0-GGUF

llama-cpp
18
1

Phi-3-medium-4k-instruct-Q6_K-GGUF

llama-cpp
18
1

Qwen2-7B-Q5_0-GGUF

NaNK
llama-cpp
18
1

tabula-8b-Q5_0-GGUF

NaNK
llama-cpp
18
1

RoGemma-7b-Instruct-Q5_0-GGUF

NaNK
18
1

Mistral-Nemo-Instruct-2407-Q5_K_S-GGUF

NaNK
llama-cpp
18
1

granite-3.0-8b-instruct-Q8_0-GGUF

NaNK
llama-cpp
18
1

BgGPT-Gemma-2-2.6B-IT-v1.0-Q8_0-GGUF

NaNK
llama-cpp
18
1

lb-reranker-0.5B-v1.0-Q8_0-GGUF

NaNK
llama-cpp
18
1

Dans-PersonalityEngine-V1.3.0-12b-Q5_K_M-GGUF

NikolayKozloff/Dans-PersonalityEngine-V1.3.0-12b-Q5KM-GGUF This model was converted to GGUF format from `PocketDoc/Dans-PersonalityEngine-V1.3.0-12b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
18
1

Dhanishtha-2.0-preview-Q4_K_S-GGUF

NaNK
llama-cpp
18
1

gemma-3-4b-it-shqip-v3-Q8_0-GGUF

NaNK
llama-cpp
18
1

DeepSeek-R1-Distill-Qwen-1.5B-Multilingual-Q8_0-GGUF

NikolayKozloff/DeepSeek-R1-Distill-Qwen-1.5B-Multilingual-Q80-GGUF This model was converted to GGUF format from `lightblue/DeepSeek-R1-Distill-Qwen-1.5B-Multilingual` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
17
3

helium-1-2b-Q8_0-GGUF

NikolayKozloff/helium-1-2b-Q80-GGUF This model was converted to GGUF format from `kyutai/helium-1-2b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
17
3

L3-8B-Lunaris-v1-IQ4_NL-GGUF

NaNK
llama-cpp
17
2

Hermes-3-Llama-3.2-3B-Q8_0-GGUF

NaNK
Llama-3
17
2

Hunyuan-1.8B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
17
2

granite-20b-code-base-Q3_K_L-GGUF

NaNK
llama-cpp
17
1

strela-Q5_0-GGUF

llama-cpp
17
1

SauerkrautLM-Gemma-2b-Q8_0-GGUF

NaNK
llama-cpp
17
1

GermanEduScorer-Qwen2-1.5b-Q8_0-GGUF

NaNK
llama-cpp
17
1

Viking-7B-Q5_K_S-GGUF

NaNK
llama-cpp
17
1

Llama-3-Instruct-Neurona-8b-v2-Q4_0-GGUF

NaNK
llama-cpp
17
1

magnum-12b-v2.5-kto-Q6_K-GGUF

NaNK
llama-cpp
17
1

saiga_nemo_12b-Q6_K-GGUF

NaNK
llama-cpp
17
1

Pensez-v0.1-e5-Q8_0-GGUF

NaNK
llama-cpp
17
1

gemma-3-12b-it-Q8_0-GGUF

NaNK
llama-cpp
17
1

Llasa-1B-Q8_0-GGUF

NikolayKozloff/Llasa-1B-Q80-GGUF This model was converted to GGUF format from `HKUST-Audio/Llasa-1B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
16
3

bleta-8B-v0.5-Albanian-shqip-GGUF

NaNK
16
2

Phi-3-medium-4k-instruct-Q5_K_S-GGUF

llama-cpp
16
2

GigaChat-20B-A3B-instruct-Q3_K_L-GGUF

NaNK
llama-cpp
16
2

q1-3B-PRIME-Q8_0-GGUF

NaNK
llama-cpp
16
2

mGPT-1.3B-uzbek-GGUF

NaNK
llama-cpp
16
1

polanka-qwen2-3b-v0.1-Q8_0-GGUF

NaNK
llama-cpp
16
1

Qwen2-1.5B-Ita-Q8_0-GGUF

NaNK
llama-cpp
16
1

Replete-Coder-Llama3-8B-IQ4_NL-GGUF

NaNK
16
1

NuminaMath-7B-TIR-IQ4_NL-GGUF

NaNK
llama-cpp
16
1

it-5.4-fp16-orpo-v2-Q8_0-GGUF

NaNK
llama-cpp
16
1

Tiger-Gemma-9B-v1-Q4_0-GGUF

NaNK
llama-cpp
16
1

WoonaV1.2-9b-Q8_0-GGUF

NaNK
llama-cpp
16
1

jais-13b-chat-Q5_K_M-GGUF

NaNK
llama-cpp
16
1

Phi-4-reasoning-Q5_K_S-GGUF

llama-cpp
16
1

AceReason-Nemotron-14B-Q5_K_S-GGUF

NaNK
llama-cpp
16
1

NextCoder-7B-Q8_0-GGUF

NaNK
llama-cpp
16
1

CodeQwen1.5-7B-Q8_0-GGUF

NaNK
llama-cpp
15
4

OpenCoder-8B-Instruct-Q5_K_M-GGUF

NaNK
llama-cpp
15
3

Llama-3-8B-Swedish-Norwegian-Danish-chekpoint-18833-1-epoch-15_6_2024-Q8_0-GGUF

NaNK
llama
15
2

gemma2-9B-sunfall-v0.5-Q8_0-GGUF

NaNK
llama-cpp
15
2

Qwen-portuguese-luana-7b-GGUF

NaNK
llama-cpp
15
1

Llama-3-8B-instruct-dansk-Q8_0-GGUF

NaNK
llama-cpp
15
1

Dorna-Llama3-8B-Instruct-IQ4_NL-GGUF

NaNK
llama-3
15
1

llama3-turbcat-instruct-8b-IQ4_NL-GGUF

NaNK
llama-cpp
15
1

Llama-3SOME-8B-v2-Q4_K_S-GGUF

NaNK
llama-cpp
15
1

Replete-Coder-Qwen2-1.5b-Q8_0-GGUF

NaNK
15
1

gemma-2-9b-Q8_0-GGUF

NaNK
llama-cpp
15
1

Qwen2-1.5B-ITA-Instruct-Q8_0-GGUF

NaNK
llama-cpp
15
1

Tiger-Gemma-9B-v1-IQ4_NL-GGUF

NaNK
llama-cpp
15
1

Mistral-Nemo-Instruct-2407-Q5_K_M-GGUF

NaNK
llama-cpp
15
1

SauerkrautLM-Nemo-12b-Instruct-Q5_K_M-GGUF

NaNK
llama-cpp
15
1

Viking-Magnum-v0.1-7B-Q8_0-GGUF

NaNK
llama
15
1

BgGPT-Gemma-2-27B-IT-v1.0-Q2_K-GGUF

NaNK
llama-cpp
15
1

EXAONE-3.5-2.4B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
15
1

granite-3.1-8b-instruct-Q8_0-GGUF

NaNK
llama-cpp
15
1

EXAONE-Deep-2.4B-Q8_0-GGUF

NaNK
llama-cpp
15
1

Dhanishtha-2.0-preview-Q5_K_S-GGUF

NikolayKozloff/Dhanishtha-2.0-preview-Q5KS-GGUF This model was converted to GGUF format from `HelpingAI/Dhanishtha-2.0-preview` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
15
1

MAmmoTH-Coder-7B-GGUF

NaNK
15
0

granite-8b-code-base-Q8_0-GGUF

NaNK
llama-cpp
14
5

llama3_8b_chat_brainstorm-Q6_K-GGUF

NaNK
llama-cpp
14
3

granite-8b-code-instruct-Q6_K-GGUF

NaNK
llama-cpp
14
2

Mistral-Nemo-Kurdish-Q6_K-GGUF

llama-cpp
14
2

phi-4-Q4_K_M-GGUF

NaNK
llama-cpp
14
2

ArmenianGPT-0.5-12B-Q8_0-GGUF

NikolayKozloff/ArmenianGPT-0.5-12B-Q80-GGUF This model was converted to GGUF format from `ArmGPT/ArmenianGPT-0.5-12B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
14
2

Mixtral_AI_CyberTron_Swahili_7b-GGUF

NaNK
llama-cpp
14
1

llama-3-typhoon-v1.5-8b-instruct-Q6_K-GGUF

NaNK
llama-cpp
14
1

internlm2-math-plus-20b-Q4_0-GGUF

NaNK
llama-cpp
14
1

llama3-tweety-8b-italian-Q4_0-GGUF

NaNK
llama-cpp
14
1

L3-8B-Lunaris-v1-Q4_0-GGUF

NaNK
llama-cpp
14
1

gemma-2-27b-Q2_K-GGUF

NaNK
llama-cpp
14
1

RoGemma-7b-Instruct-Q4_K_L-GGUF

NaNK
14
1

Replete-Coder-Instruct-8b-Merged-Q8_0-GGUF

NaNK
llama-cpp
14
1

Tiger-Gemma-9B-v1-Q8_0-GGUF

NaNK
llama-cpp
14
1

mistral-doryV2-12b-Q8_0-GGUF

NaNK
llama-cpp
14
1

OmniLing-V1-8b-experimental-Q8_0-GGUF

NaNK
llama-cpp
14
1

Phi-3-medium-4k-instruct-sq-LORA-F16-GGUF

llama-cpp
14
1

Phi-3-medium-4k-instruct-sq-LORA-Q8_0-GGUF

llama-cpp
14
1

OpenCoder-8B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
14
1

GigaChat-20B-A3B-instruct-Q2_K-GGUF

NaNK
llama-cpp
14
1

cogito-v1-preview-qwen-14B-Q4_K_S-GGUF

NaNK
llama-cpp
14
1

Confucius3-Math-Q5_K_S-GGUF

llama-cpp
14
1

Datarus-R1-14B-preview-Q4_K_M-GGUF

NikolayKozloff/Datarus-R1-14B-preview-Q4KM-GGUF This model was converted to GGUF format from `DatarusAI/Datarus-R1-14B-preview` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
14
1

YanoljaNEXT-Rosetta-12B-Q8_0-GGUF

NaNK
llama-cpp
14
1

Llama3-DocChat-1.0-8B-Q8_0-GGUF

NaNK
llama-3
13
6

SambaLingo-Hungarian-Chat-GGUF

13
3

Ko-Qwen2-7B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
13
3

Replete-LLM-Qwen2-7b_Beta-Preview-Q8_0-GGUF

NaNK
llama-cpp
13
2

Mistral-NeMo-Minitron-8B-Base-Q8_0-GGUF

NaNK
llama-cpp
13
2

Muyan-TTS-Q8_0-GGUF

llama-cpp
13
2

suzume-llama-3-8B-multilingual-orpo-borda-full-Q8_0-GGUF

NaNK
llama-cpp
13
1

Qwen2-7B-Instruct-Q5_K_S-GGUF

NaNK
llama-cpp
13
1

leniachat-qwen2-1.5B-v0-Q8_0-GGUF

NaNK
llama-cpp
13
1

LLAMA-3_8B_Unaligned_Alpha-Q8_0-GGUF

NaNK
llama-cpp
13
1

tabula-8b-IQ4_NL-GGUF

NaNK
llama-cpp
13
1

Gemma-2-9B-It-SPPO-Iter3-IQ4_XS-GGUF

NaNK
llama-cpp
13
1

RoGemma-7b-Instruct-Q4_0-GGUF

NaNK
13
1

RoGemma-7b-Instruct-Q6_K_L-GGUF

NaNK
13
1

RoGemma-7b-Instruct-Q5_K_L-GGUF

NaNK
13
1

Viking-13B-Q4_0-GGUF

NaNK
llama-cpp
13
1

Llama-3-Instruct-Neurona-8b-v2-Q5_0-GGUF

NaNK
llama-cpp
13
1

RoLlama3-8b-Instruct-Q4_K_L-GGUF

NaNK
13
1

MegaBeam-Mistral-7B-512k-Q8_0-GGUF

NaNK
llama-cpp
13
1

Llama-3.1-SauerkrautLM-8b-Instruct-Q8_0-GGUF

NaNK
llama-cpp
13
1

Bielik-11B-v2.3-Instruct-Q5_K_M-GGUF

NaNK
llama-cpp
13
1

Mistral-Nemo-Instruct-bellman-12b-Q5_K_M-GGUF

NaNK
llama-cpp
13
1

GigaChat-20B-A3B-instruct-Q4_K_S-GGUF

NaNK
llama-cpp
13
1

AceInstruct-7B-Q8_0-GGUF

NaNK
llama-cpp
13
1

amoral-gemma3-12B-Q8_0-GGUF

NaNK
llama-cpp
13
1

NVIDIA-Nemotron-Nano-12B-v2-Q5_K_M-GGUF

NikolayKozloff/NVIDIA-Nemotron-Nano-12B-v2-Q5KM-GGUF This model was converted to GGUF format from `nvidia/NVIDIA-Nemotron-Nano-12B-v2` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
13
1

Hermes-4-14B-Q5_K_S-GGUF

NikolayKozloff/Hermes-4-14B-Q5KS-GGUF This model was converted to GGUF format from `NousResearch/Hermes-4-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
13
1

Llama-3.1-Minitron-4B-Width-Base-Q8_0-GGUF

NaNK
llama-cpp
12
8

PULI-LlumiX-32K-GGUF

12
4

Meltemi-7B-v1-GGUF

NaNK
12
3

Aura-Llama-Abliterated-Q8_0-GGUF

NaNK
llama-cpp
12
2

LongWriter-llama3.1-8b-Q8_0-GGUF

NaNK
llama
12
2

Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3-Q8_0-GGUF

NaNK
llama
12
2

NVIDIA-Nemotron-Nano-12B-v2-Q6_K-GGUF

NikolayKozloff/NVIDIA-Nemotron-Nano-12B-v2-Q6K-GGUF This model was converted to GGUF format from `nvidia/NVIDIA-Nemotron-Nano-12B-v2` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
12
2

llama-7b-finnish-v2-Q8_0-GGUF

NaNK
llama
12
1

Llama-3-KafkaLM-8B-v0.1-Q8_0-GGUF

NaNK
llama3
12
1

Yi-1.5-9B-Chat-Q4_K_M-GGUF

NaNK
llama-cpp
12
1

tyr-Q8_0-GGUF

NaNK
llama-cpp
12
1

Llama-3-Instruct-8B-SimPO-Q5_0-GGUF

NaNK
llama-cpp
12
1

AlchemistCoder-DS-6.7B-Q5_0-GGUF

NaNK
llama-cpp
12
1

Llama-3-Oasis-v1-OAS-8B-Q4_0-GGUF

NaNK
llama-cpp
12
1

Llama-3-neoAI-8B-Chat-v0.1-Q4_0-GGUF

NaNK
llama-cpp
12
1

Llama-3-Instruct-Neurona-8b-v2-IQ4_NL-GGUF

NaNK
llama-cpp
12
1

SeaLLM3-7B-Chat-Q8_0-GGUF

NaNK
llama-cpp
12
1

ArliAI-Llama-3-8B-Formax-v1.0-Q5_0-GGUF

NaNK
llama-cpp
12
1

ArliAI-Llama-3-8B-Formax-v1.0-IQ4_NL-GGUF

NaNK
llama-cpp
12
1

NuminaMath-7B-TIR-Q8_0-GGUF

NaNK
llama-cpp
12
1

SauerkrautLM-Nemo-12b-Instruct-Q8_0-GGUF

NaNK
llama-cpp
12
1

SauerkrautLM-Nemo-12b-Instruct-Q6_K-GGUF

NaNK
llama-cpp
12
1

falcon-mamba-7b-Q8_0-GGUF

NaNK
llama-cpp
12
1

Viking-SlimSonnet-v1-7B-Q8_0-GGUF

NaNK
llama
12
1

OpenCoder-8B-Instruct-Q6_K-GGUF

NaNK
llama-cpp
12
1

BgGPT-Gemma-2-9B-IT-v1.0-Q8_0-GGUF

NaNK
llama-cpp
12
1

amoral-gemma3-12B-Q6_K-GGUF

NaNK
llama-cpp
12
1

Qwen3-14B-Q5_K_S-GGUF

NaNK
llama-cpp
12
1

NextCoder-14B-Q4_K_M-GGUF

NikolayKozloff/NextCoder-14B-Q4KM-GGUF This model was converted to GGUF format from `microsoft/NextCoder-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
12
1

YanoljaNEXT-Rosetta-12B-2510-Q5_K_S-GGUF

NaNK
llama-cpp
12
1

DeepSeek-R1-ReDistill-Qwen-7B-v1.1-Q8_0-GGUF

NaNK
llama-cpp
11
3

Seed-X-Instruct-7B-Q8_0-GGUF

NaNK
llama-cpp
11
2

Diver-Retriever-4B-Q8_0-GGUF

NaNK
llama-cpp
11
2

Llama-3-8b-ita-ties-Q8_0-GGUF

NaNK
llama-cpp
11
1

Phi-3-medium-128k-instruct-Q4_0-GGUF

llama-cpp
11
1

Llama-3-Instruct-8B-SimPO-Q4_0-GGUF

NaNK
llama-cpp
11
1

shotor-Q8_0-GGUF

llama-cpp
11
1

Llama-3-Instruct-8B-SPPO-Iter3-IQ4_NL-GGUF

NaNK
llama-cpp
11
1

Arcee-Spark-FP32-Q8_0-GGUF

NaNK
llama-cpp
11
1

Viking-7B-Q4_0-GGUF

NaNK
llama-cpp
11
1

gemma-2-9b-it-Q8_0-GGUF

NaNK
llama-cpp
11
1

RoLlama3-8b-Instruct-Q8_0_L-GGUF

NaNK
11
1

gemma2-9B-daybreak-v0.5-Q8_0-GGUF

NaNK
llama-cpp
11
1

Einstein-v7-Qwen2-7B-Q8_0-GGUF

NaNK
llama-cpp
11
1

Gemma-2-9b-indic-Q8_0-GGUF

NaNK
llama-cpp
11
1

Mistral-Nemo-Instruct-2407-Q6_K-GGUF

NaNK
llama-cpp
11
1

Replete-LLM-V2.5-Qwen-1.5b-Q8_0-GGUF

NaNK
llama-cpp
11
1

Replete-LLM-V2.5-Qwen-32b-Q3_K_S-GGUF

NaNK
llama-cpp
11
1

Mistral-Nemo-Kurdish-Instruct-Q5_K_S-GGUF

llama-cpp
11
1

qwen2.5-7b-ins-v3-Q8_0-GGUF

NaNK
llama-cpp
11
1

phi-4-Q5_K_S-GGUF

NaNK
llama-cpp
11
1

zeta-Q8_0-GGUF

llama-cpp
11
1

Meta-Llama-3.1-8B-SurviveV3-Q8_0-GGUF

NikolayKozloff/Meta-Llama-3.1-8B-SurviveV3-Q80-GGUF This model was converted to GGUF format from `lolzinventor/Meta-Llama-3.1-8B-SurviveV3` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
11
1

Qwen3-0.6B-Q8_0-GGUF

NaNK
llama-cpp
11
1

AceReason-Nemotron-1.1-7B-Q8_0-GGUF

NikolayKozloff/AceReason-Nemotron-1.1-7B-Q80-GGUF This model was converted to GGUF format from `nvidia/AceReason-Nemotron-1.1-7B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
11
1

OpenCodeReasoning-Nemotron-1.1-7B-Q8_0-GGUF

NikolayKozloff/OpenCodeReasoning-Nemotron-1.1-7B-Q80-GGUF This model was converted to GGUF format from `nvidia/OpenCodeReasoning-Nemotron-1.1-7B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
11
1

OpenCodeReasoning-Nemotron-1.1-14B-Q4_K_M-GGUF

NikolayKozloff/OpenCodeReasoning-Nemotron-1.1-14B-Q4KM-GGUF This model was converted to GGUF format from `nvidia/OpenCodeReasoning-Nemotron-1.1-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
11
1

OpenReasoning-Nemotron-7B-Q8_0-GGUF

NikolayKozloff/OpenReasoning-Nemotron-7B-Q80-GGUF This model was converted to GGUF format from `nvidia/OpenReasoning-Nemotron-7B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
11
1

Piaget-1.7B-Q8_0-GGUF

NikolayKozloff/Piaget-1.7B-Q80-GGUF This model was converted to GGUF format from `gustavecortal/Piaget-1.7B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
11
1

YanoljaNEXT-Rosetta-12B-Q4_K_M-GGUF

NaNK
llama-cpp
11
1

tora-13b-v1.0

NaNK
11
0

h2o-danube3-500m-base-Q8_0-GGUF

llama-cpp
10
2

Sailor-7B-Q8_0-GGUF

NaNK
llama-cpp
10
1

Nxcode-CQ-7B-orpo-Q6_K-GGUF

NaNK
llama-cpp
10
1

Falcon2-5.5B-Swedish-Q8_0-GGUF

NaNK
llama-cpp
10
1

Alphacode-MALI-9B-Q8_0-GGUF

NaNK
llama-cpp
10
1

Phi-3-medium-4k-instruct-Q4_0-GGUF

llama-cpp
10
1

Phi-3-medium-128k-instruct-Q5_K_S-GGUF

llama-cpp
10
1

Awanllm-Llama-3-8B-Cumulus-v0.3.2-Q5_0-GGUF

NaNK
llama-cpp
10
1

AlchemistCoder-DS-6.7B-Q4_0-GGUF

NaNK
llama-cpp
10
1

Llama-3-Steerpike-v1-OAS-8B-Q5_0-GGUF

NaNK
llama-cpp
10
1

h2o-Llama-3-8B-Japanese-Instruct-Q8_0-GGUF

NaNK
llama-cpp
10
1

Llama-3-Instruct-8B-SPPO-Iter3-Q4_0-GGUF

NaNK
llama-cpp
10
1

Turkish-Llama-8b-Instruct-v0.1-IQ4_NL-GGUF

NaNK
Llama
10
1

Viking-7B-Q8_0-GGUF

NaNK
llama-cpp
10
1

RoGemma-7b-Instruct-Q8_0-GGUF

NaNK
10
1

RoLlama3-8b-Instruct-Q5_K_L-GGUF

NaNK
10
1

Viking-13B-Q4_K_M-GGUF

NaNK
llama-cpp
10
1

ParaLex-Llama-3-8B-SFT-Q8_0-GGUF

NaNK
llama-cpp
10
1

ArliAI-Llama-3-8B-Formax-v1.0-Q4_0-GGUF

NaNK
llama-cpp
10
1

mathstral-7B-v0.1-Q8_0-GGUF

NaNK
llama-cpp
10
1

falcon-mamba-7b-instruct-Q8_0-GGUF

NaNK
llama-cpp
10
1

jais-13b-chat-Q3_K_L-GGUF

NaNK
llama-cpp
10
1

Mistral-Small-Instruct-2409-Q3_K_L-GGUF

NaNK
llama-cpp
10
1

Mistral-Small-Instruct-2409-Q2_K-GGUF

NaNK
llama-cpp
10
1

polanka-qwen2-1.5b-v0.1-ckpt_401000-Q8_0-GGUF

NaNK
llama-cpp
10
1

Replete-LLM-V2.5-Qwen-14b-Q5_K_M-GGUF

NaNK
llama-cpp
10
1

OpenCoder-1.5B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
10
1

FuseChat-Qwen-2.5-7B-Instruct-Q8_0-GGUF

NikolayKozloff/FuseChat-Qwen-2.5-7B-Instruct-Q80-GGUF This model was converted to GGUF format from `FuseAI/FuseChat-Qwen-2.5-7B-Instruct` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
10
1

Human-Like-Mistral-Nemo-Instruct-2407-Q6_K-GGUF

NaNK
llama-cpp
10
1

GLM-Z1-9B-0414-Q8_0-GGUF

NaNK
llama-cpp
10
1

Polaris-4B-Preview-Q8_0-GGUF

NaNK
llama-cpp
10
1

OpenCodeReasoning-Nemotron-1.1-14B-Q5_K_S-GGUF

NikolayKozloff/OpenCodeReasoning-Nemotron-1.1-14B-Q5KS-GGUF This model was converted to GGUF format from `nvidia/OpenCodeReasoning-Nemotron-1.1-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
10
1

MiniCPM4.1-8B-Q5_K_S-GGUF

NikolayKozloff/MiniCPM4.1-8B-Q5KS-GGUF This model was converted to GGUF format from `openbmb/MiniCPM4.1-8B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
10
1

ArmenianGPT-0.5-12B-Q4_K_M-GGUF

NikolayKozloff/ArmenianGPT-0.5-12B-Q4KM-GGUF This model was converted to GGUF format from `ArmGPT/ArmenianGPT-0.5-12B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
10
1

SauerkrautLM-3b-v1

NaNK
10
0

SauerkrautLM-13b-v1

NaNK
10
0

SFR-SFT-LLaMA-3-8B-R-Q8_0-GGUF

NaNK
llama-cpp
9
5

SFR-Iterative-DPO-LLaMA-3-8B-R-Q8_0-GGUF

NaNK
llama-cpp
9
4

Llama-3.1-Hawkish-8B-Q8_0-GGUF

NikolayKozloff/Llama-3.1-Hawkish-8B-Q80-GGUF This model was converted to GGUF format from `mukaj/Llama-3.1-Hawkish-8B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-3.1
9
4

Llama-3-8B-dutch-GGUF

NaNK
llama 3 8B
9
3

llama-3-llamilitary-Q8_0-GGUF

llama-cpp
9
3

Meta-Llama-3.1-8B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
9
3

granite-3b-code-base-Q8_0-GGUF

NaNK
llama-cpp
9
2

AutoCoder_S_6.7B-Q8_0-GGUF

NaNK
llama-cpp
9
2

Irbis-7b-v0.1-Kazakh-Q8_0-GGUF

NaNK
llama-cpp
9
2

bella-1-8b-Q8_0-GGUF

NaNK
llama-cpp
9
2

Mistral-Nemo-12B-ArliAI-RPMax-v1.1-Q5_K_M-GGUF

NaNK
llama-cpp
9
2

tora-7b-v1.0

NaNK
9
1

SambaLingo-Bulgarian-Chat-GGUF

9
1

Llama-3-portuguese-Tom-cat-8b-instruct-Q6_K-GGUF

NaNK
llama-cpp
9
1

openchat-3.6-8b-20240522-Q8_0-GGUF

NaNK
llama3
9
1

L3-Aethora-15B-Q5_K_S-GGUF

NaNK
llama-factory
9
1

L3-Aethora-15B-Q6_K-GGUF

NaNK
llama-factory
9
1

L3-Aethora-15B-Q5_0-GGUF

NaNK
llama-factory
9
1

Ko-Llama-3-8B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
9
1

Tiger-Gemma-9B-v1-Q5_0-GGUF

NaNK
llama-cpp
9
1

Meta-Llama-3.1-8B-Q8_0-GGUF

NaNK
llama-3
9
1

mistral-doryV2-12b-Q6_K-GGUF

NaNK
llama-cpp
9
1

Llama-3.1-Minitron-4B-Depth-Base-Q8_0-GGUF

NaNK
llama-cpp
9
1

Viking-SlimSonnet-v0.2-7B-Q8_0-GGUF

NaNK
llama
9
1

ChatFrame-Instruct-Persian-Small-Q8_0-GGUF

llama-cpp
9
1

pansophic-1-preview-LLaMA3.1-8b-Q8_0-GGUF

NaNK
llama-cpp
9
1

MagpieLM-4B-Chat-v0.1-Q8_0-GGUF

NaNK
llama-cpp
9
1

Replete-LLM-V2.5-Qwen-7b-Q8_0-GGUF

NaNK
llama-cpp
9
1

Replete-LLM-V2.5-Qwen-0.5b-Q8_0-GGUF

NaNK
llama-cpp
9
1

Llama-eus-8B-Q8_0-GGUF

NaNK
llama-cpp
9
1

OpenCoder-1.5B-Base-Q8_0-GGUF

NaNK
llama-cpp
9
1

FuseChat-Gemma-2-9B-Instruct-Q8_0-GGUF

NikolayKozloff/FuseChat-Gemma-2-9B-Instruct-Q80-GGUF This model was converted to GGUF format from `FuseAI/FuseChat-Gemma-2-9B-Instruct` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
9
1

DeepSeek-R1-Distill-Qwen-14B-Multilingual-Q5_K_S-GGUF

NaNK
llama-cpp
9
1

Phi-4-reasoning-plus-Q4_K_M-GGUF

NikolayKozloff/Phi-4-reasoning-plus-Q4KM-GGUF This model was converted to GGUF format from `microsoft/Phi-4-reasoning-plus` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

llama-cpp
9
1

ERNIE-4.5-0.3B-PT-Q8_0-GGUF

NikolayKozloff/ERNIE-4.5-0.3B-PT-Q80-GGUF This model was converted to GGUF format from `baidu/ERNIE-4.5-0.3B-PT` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
9
1

Dhanishtha-2.0-preview-Q4_K_M-GGUF

NaNK
llama-cpp
9
1

OpenCodeReasoning-Nemotron-1.1-14B-Q4_K_S-GGUF

NikolayKozloff/OpenCodeReasoning-Nemotron-1.1-14B-Q4KS-GGUF This model was converted to GGUF format from `nvidia/OpenCodeReasoning-Nemotron-1.1-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
9
1

ArmenianGPT-0.1-12B-Q5_K_M-GGUF

NikolayKozloff/ArmenianGPT-0.1-12B-Q5KM-GGUF This model was converted to GGUF format from `ArmGPT/ArmenianGPT-0.1-12B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
9
1

ERNIE-4.5-21B-A3B-Thinking-Q3_K_S-GGUF

NikolayKozloff/ERNIE-4.5-21B-A3B-Thinking-Q3KS-GGUF This model was converted to GGUF format from `baidu/ERNIE-4.5-21B-A3B-Thinking` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
9
1

YandexGPT-5-Lite-8B-pretrain-Q8_0-GGUF

NaNK
llama-cpp
8
5

L3-Aethora-15B-V2-Q5_K_S-GGUF

NaNK
llama-cpp
8
3

Selene-1-Mini-Llama-3.1-8B-Q6_K-GGUF

NaNK
llama
8
3

Chocolatine-8B-Instruct-DPO-v1.0-Q8_0-GGUF

NaNK
llama3
8
2

L3-Aethora-15B-V2-Q4_K_M-GGUF

NaNK
llama-cpp
8
2

L3-8B-Everything-COT-Q8_0-GGUF

NaNK
llama
8
2

L3-8B-Celeste-V1.2-Q8_0-GGUF

NaNK
llama-factory
8
2

llama-3-Nephilim-v3-8B-Q8_0-GGUF

NaNK
llama-cpp
8
2

orcapaca_albanian-Q5_K_M-GGUF

llama-factory
8
2

NightyGurps-12b-v1-experimental-Q8_0-GGUF

NaNK
llama-cpp
8
2

Dans-PersonalityEngine-V1.3.0-12b-Q6_K-GGUF

NikolayKozloff/Dans-PersonalityEngine-V1.3.0-12b-Q6K-GGUF This model was converted to GGUF format from `PocketDoc/Dans-PersonalityEngine-V1.3.0-12b` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
8
2

ALMA-7B-GGUF

NaNK
8
1

Heidrun-Mistral-7B-chat-Q8_0-GGUF

NaNK
llama-cpp
8
1

MATH-BG-v1-7B-GGUF

NaNK
llama-cpp
8
1

dictalm2.0-instruct-Q6_K-GGUF

NaNK
llama-cpp
8
1

malaysian-llama-3-8b-instruct-16k-Q8_0-GGUF

NaNK
llama-cpp
8
1

EVA-GPT-German-v7-2-Beta-Q5_K_M-GGUF

llama-cpp
8
1

shisa-v1-llama3-8b-Q8_0-GGUF

NaNK
llama-cpp
8
1

Awanllm-Llama-3-8B-Cumulus-v0.3.2-Q4_0-GGUF

NaNK
llama-cpp
8
1

Llama3-German-8B-Q8_0-GGUF

NaNK
llama-cpp
8
1

Llama3-DiscoLeo-Instruct-8B-v0.1-Q8_0-GGUF

NaNK
llama-cpp
8
1

Llama3-DiscoLeo-Instruct-8B-32k-v0.1-Q8_0-GGUF

NaNK
llama-cpp
8
1

suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_M-GGUF

NaNK
llama-cpp
8
1

suzume-llama-3-8B-multilingual-orpo-borda-top75-Q8_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-11.5B-V2-Q4_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-11.5B-Instruct-V2-Q5_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-Ultron-Q8_0-GGUF

llama-cpp
8
1

Awanllm-Llama-3-8B-Cumulus-v1.0-Q4_0-GGUF

NaNK
llama-cpp
8
1

Awanllm-Llama-3-8B-Cumulus-v1.0-Q5_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-8B-instruct-Swedish-Norwegian-Danish-Q8_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-8B-Swedish-Norwegian-Danish-checkpoint-11525-03_6_2024-Q8_0-GGUF

NaNK
llama
8
1

L3-Aethora-15B-Q4_K_S-GGUF

NaNK
llama-factory
8
1

L3-Aethora-15B-Q5_K_M-GGUF

NaNK
llama-factory
8
1

L3-Aethora-15B-Q8_0-GGUF

NaNK
llama-factory
8
1

L3-Aethora-15B-Q4_0-GGUF

NaNK
llama-factory
8
1

Llama-3-8B-Swedish-Norwegian-Danish-checkpoint-14375-08_06_2024-Q8_0-GGUF

NaNK
llama
8
1

Llama-3-Oasis-v1-OAS-8B-Q5_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-Steerpike-v1-OAS-8B-Q4_0-GGUF

NaNK
llama-cpp
8
1

CataLlama-v0.1-Instruct-SFT-Q8_0-GGUF

llama
8
1

CataLlama-v0.1-Instruct-DPO-Q8_0-GGUF

llama
8
1

Tesser-Llama-3-Ko-8B-Q5_0-GGUF

NaNK
llama-cpp
8
1

Dorna-Llama3-8B-Instruct-IQ4_XS-GGUF

NaNK
llama-3
8
1

SauerkrautLM-1.5b-Q4_0-GGUF

NaNK
llama-cpp
8
1

tabula-8b-Q4_0-GGUF

NaNK
llama-cpp
8
1

Morfoz-LLM-8b-v1.0-IQ4_NL-GGUF

NaNK
llama-cpp
8
1

Llama-3-Instruct-8B-SPPO-Iter3-Q5_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-neoAI-8B-Chat-v0.1-Q5_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-neoAI-8B-Chat-v0.1-IQ4_NL-GGUF

NaNK
llama-cpp
8
1

RoLlama3-8b-Instruct-Q5_0-GGUF

NaNK
llama-cpp
8
1

RoLlama3-8b-Instruct-Q6_K_L-GGUF

NaNK
8
1

Viking-13B-Q5_K_M-GGUF

NaNK
llama-cpp
8
1

bella-2-8b-Q8_0-GGUF

NaNK
llama-cpp
8
1

ArliAI-Llama-3-8B-Formax-v1.0-IQ4_XS-GGUF

NaNK
llama-cpp
8
1

mistral-doryV2-12b-Q5_K_M-GGUF

NaNK
llama-cpp
8
1

mistral-doryV2-12b-Q5_K_S-GGUF

NaNK
llama-cpp
8
1

L3.1-8B-Celeste-V1.5-Q8_0-GGUF

NaNK
llama-cpp
8
1

uzbek-llama-3.1-8B-instruct-v2-Q8_0-GGUF

NaNK
llama
8
1

Duet_Minitron8b_v0.5-Q8_0-GGUF

NaNK
llama-cpp
8
1

ChatFrame-Q8_0-GGUF

llama-cpp
8
1

Mistral-Nemo-12B-ArliAI-RPMax-v1.1-Q6_K-GGUF

NaNK
llama-cpp
8
1

Llama-3.1-8B-ArliAI-RPMax-v1.1-Q8_0-GGUF

NaNK
llama-cpp
8
1

jais-13b-chat-Q3_K_S-GGUF

NaNK
llama-cpp
8
1

MagpieLM-8B-SFT-v0.1-Q8_0-GGUF

NaNK
llama-cpp
8
1

Replete-LLM-V2.5-Qwen-14b-Q5_K_S-GGUF

NaNK
llama-cpp
8
1

Replete-LLM-V2.5-Qwen-32b-Q4_K_M-GGUF

NaNK
llama-cpp
8
1

Mistral-NeMo-Minitron-8B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
8
1

FastApply-1.5B-v1.0-Q6_K-GGUF

NaNK
llama-cpp
8
1

OpenCoder-8B-Instruct-Q5_K_S-GGUF

NaNK
llama-cpp
8
1

Teuken-7B-instruct-research-v0.4-Q8_0-GGUF

NaNK
llama-cpp
8
1

Llama-3-ChocoLlama-8B-instruct-Q8_0-GGUF

NaNK
llama-cpp
8
1

SauerkrautLM-v2-14b-DPO-Q5_K_M-GGUF

NikolayKozloff/SauerkrautLM-v2-14b-DPO-Q5KM-GGUF This model was converted to GGUF format from `VAGOsolutions/SauerkrautLM-v2-14b-DPO` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
8
1

OREAL-7B-Q8_0-GGUF

NaNK
llama-cpp
8
1

Qwen3-14B-Q4_K_S-GGUF

NaNK
llama-cpp
8
1

Phi-4-reasoning-Q4_K_S-GGUF

NikolayKozloff/Phi-4-reasoning-Q4KS-GGUF This model was converted to GGUF format from `microsoft/Phi-4-reasoning` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

llama-cpp
8
1

Llama-3.1-Nemotron-Nano-4B-v1.1-Q8_0-GGUF

NikolayKozloff/Llama-3.1-Nemotron-Nano-4B-v1.1-Q80-GGUF This model was converted to GGUF format from `nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-3
8
1

OpenReasoning-Nemotron-14B-Q5_K_S-GGUF

NikolayKozloff/OpenReasoning-Nemotron-14B-Q5KS-GGUF This model was converted to GGUF format from `nvidia/OpenReasoning-Nemotron-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
8
1

OpenReasoning-Nemotron-14B-Q4_K_S-GGUF

NikolayKozloff/OpenReasoning-Nemotron-14B-Q4KS-GGUF This model was converted to GGUF format from `nvidia/OpenReasoning-Nemotron-14B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
8
1

Hunyuan-4B-Instruct-Q8_0-GGUF

NaNK
llama-cpp
8
1

Goedel-Prover-V2-8B-Q8_0-GGUF

NikolayKozloff/Goedel-Prover-V2-8B-Q80-GGUF This model was converted to GGUF format from `Goedel-LM/Goedel-Prover-V2-8B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
8
1

HyGPT-10b-it-Q8_0-GGUF

NaNK
llama-cpp
8
1

silly-v0.2-Q6_K-GGUF

NikolayKozloff/silly-v0.2-Q6K-GGUF This model was converted to GGUF format from `wave-on-discord/silly-v0.2` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
8
1

MiniCPM4.1-8B-Q5_K_M-GGUF

NikolayKozloff/MiniCPM4.1-8B-Q5KM-GGUF This model was converted to GGUF format from `openbmb/MiniCPM4.1-8B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

NaNK
llama-cpp
8
1

Yi-1.5-9B-Chat-Q6_K-GGUF

NaNK
llama-cpp
7
2

Llama-3SOME-8B-v2-Q5_K_S-GGUF

NaNK
llama-cpp
7
2

llama-3b-finnish-v2-GGUF

NaNK
llama
7
1

Magiq-3-Q4_0-GGUF

NaNK
llama-cpp
7
1

Minerva-1B-base-v1.0-Q6_K-GGUF

NaNK
llama-cpp
7
1

Phi-3-Large-5.6b-Q8_0-GGUF

NaNK
llama-cpp
7
1

Alphacode-MALI-11B-Q8_0-GGUF

NaNK
llama-cpp
7
1

suzume-llama-3-8B-multilingual-orpo-borda-half-Q6_K-GGUF

NaNK
llama-cpp
7
1

Llama-3-11.5B-V2-Q5_0-GGUF

NaNK
llama-cpp
7
1

Llama-3-8B-Swedish-Norwegian-Danish-checkpoint-8200-29_5_2024-Q8_0-GGUF

NaNK
llama
7
1

Llama-3SOME-8B-v2-IQ4_XS-GGUF

NaNK
llama-cpp
7
1

Morfoz-LLM-8b-v1.0-Q4_0-GGUF

NaNK
llama-cpp
7
1

Morfoz-LLM-8b-v1.0-Q5_0-GGUF

NaNK
llama-cpp
7
1

oneirogen-7B-Q4_0-GGUF

NaNK
llama-cpp
7
1

L3-8B-Lunaris-v1-Q5_0-GGUF

NaNK
llama-cpp
7
1

Viking-7B-Q4_K_M-GGUF

NaNK
llama-cpp
7
1