Ransss

101 models • 1 total models in database

Sort by:

Shadow-Crystal-12B-Q8_0-GGUF

Ransss/Shadow-Crystal-12B-Q80-GGUF This model was converted to GGUF format from `Vortex5/Shadow-Crystal-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

llama-3-Stheno-Mahou-8B-Q8_0-GGUF

NaNK

llama-cpp

Pantheon RP 1.0 8b Llama 3 Q8 0 GGUF

Ransss/Pantheon-RP-1.0-8b-Llama-3-Q80-GGUF This model was converted to GGUF format from `Gryphe/Pantheon-RP-1.0-8b-Llama-3` 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 Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

NaNK

Llama-3

L3-8B-Tamamo-v1-Q8_0-GGUF

NaNK

llama-cpp

Deepseek-R1-Distill-NSFW-RP-vRedux-Q8_0-GGUF

llama-cpp

DS-R1-Qwen3-8B-ArliAI-RpR-v4-Small-Q8_0-GGUF

NaNK

llama-cpp

L3-SthenoMaidBlackroot-15B-Q6_K-GGUF

NaNK

llama-cpp

WeirdCompound-v1.5-24b-Q6_K-GGUF

Ransss/WeirdCompound-v1.5-24b-Q6K-GGUF This model was converted to GGUF format from `FlareRebellion/WeirdCompound-v1.5-24b` 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

SOVLish-Devil-8B-L3-Q8_0-GGUF

NaNK

llama-cpp

llama-3-Nephilim-v1-8B-Q8_0-GGUF

NaNK

llama-cpp

llama3-8B-DarkIdol-2.0-Uncensored-Q8_0-GGUF

NaNK

llama3

NS-12b-DarkSluchCapV3-Q8_0-GGUF

Ransss/NS-12b-DarkSluchCapV3-Q80-GGUF This model was converted to GGUF format from `pot99rta/NS-12b-DarkSluchCapV3` 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

LLama-3-8b-Lexi-Iranian-Stories-PersianTherapist-Lumimaid-DARE_TIES-Q8_0-GGUF

NaNK

llama-cpp

L3-TheSpice-8b-v0.8.3-Q8_0-GGUF

NaNK

llama-cpp

Pantheon-RP-1.5-12b-Nemo-Q8_0-GGUF

NaNK

llama-cpp

L3-Uncen-Merger-Omelette-RP-v0.1.1-8B-Q8_0-GGUF

NaNK

llama-cpp

llama-3-Daredevil-Mahou-8B-Q8_0-GGUF

NaNK

llama-cpp

Halu-8B-Llama3-Blackroot-Q8_0-GGUF

NaNK

llama-cpp

Neural-SOVLish-Devil-8B-L3-Q8_0-GGUF

NaNK

llama-cpp

Xwin-MLewd-13B-V0.2-Q8_0-GGUF

NaNK

llama-cpp

Domain-Fusion-L3-8B-Q8_0-GGUF

NaNK

llama-cpp

L3-15B-MythicalMaid-t0.0001-Q8_0-GGUF

NaNK

llama

L3-15B-MythicalMaid-t0.0001-Q6_K-GGUF

NaNK

llama

L3-15B-EtherealMaid-t0.0001-Q6_K-GGUF

NaNK

llama

mini-magnum-12b-v1.1-Q8_0-GGUF

NaNK

llama-cpp

L3-TheGreenLion-8b-SFT-v0.1.2-Q8_0-GGUF

NaNK

llama-cpp

MN-12B-Lyra-v1-Q8_0-GGUF

NaNK

llama-cpp

YetAnotherMerge-v0.45-Q8_0-GGUF

llama-cpp

Lyralin-12B-v1-Q8_0-GGUF

NaNK

llama-cpp

Lyra_Gutenbergs-Twilight_Magnum-12B-Q8_0-GGUF

NaNK

llama-cpp

Ultracore-Instruct-12BV2-Q8_0-GGUF

Ransss/Ultracore-Instruct-12BV2-Q80-GGUF This model was converted to GGUF format from `pot99rta/Ultracore-Instruct-12BV2` 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

SOVL-Mega-Mash-V2-L3-8B-Q8_0-GGUF

NaNK

llama-cpp

TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2-Q8_0-GGUF

NaNK

llama-cpp

L3-8B-Helium3-Q8_0-GGUF

NaNK

llama-cpp

Squelching-Fantasies-qw3-14B-Q8_0-GGUF

Ransss/Squelching-Fantasies-qw3-14B-Q80-GGUF This model was converted to GGUF format from `Mawdistical/Squelching-Fantasies-qw3-14B` 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

kukuspice-7B-Q8_0-GGUF

NaNK

llama-cpp

gemma2-9B-sunfall-v0.5.2-Q8_0-GGUF

NaNK

llama-cpp

Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Quick-Q8_0-GGUF

Ransss/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Quick-Q80-GGUF This model was converted to GGUF format from `cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Quick` 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

Captain-Eris_Twilight-Mistralified-12B-Q8_0-GGUF

Ransss/Captain-ErisTwilight-Mistralified-12B-Q80-GGUF This model was converted to GGUF format from `Nitral-AI/Captain-ErisTwilight-Mistralified-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

Mistral-7B-Erebus-v3-Q8_0-GGUF

NaNK

llama-cpp

Ninja-v1-RP-Q8_0-GGUF

llama-cpp

Xwin-MLewd-13B-V0.2-Q6_K-GGUF

NaNK

llama-cpp

DarkSapling-7B-v2.0-Q8_0-GGUF

NaNK

llama-cpp

MN-Ephemeros-12B-Q8_0-GGUF

NaNK

llama-cpp

Fimbulvetr-11B-v2-Q8_0-GGUF

NaNK

llama-cpp

OpenCrystal-L3-15B-v2.1-Q6_K-GGUF

NaNK

llama-cpp

L3-TheSpice-8b-v0.1.3-Q8_0-GGUF

NaNK

llama-cpp

Kuro-Lotus-10.7B-Q8_0-GGUF

NaNK

llama-cpp

L3.1-Ablaze-Vulca-v0.1-8B-Q8_0-GGUF

NaNK

llama-cpp

OpenCrystal-15B-L3-v2-Q6_K-GGUF

NaNK

llama-cpp

Stellar-Odyssey-12b-v0.0-Q8_0-GGUF

NaNK

llama-cpp

Mistral-Nemo-12B-ArliAI-RPMax-v1.3-Q8_0-GGUF

NaNK

llama-cpp

Forgotten-Safeword-12B-v4.0-Q8_0-GGUF

NaNK

llama-cpp

Fimbulvetr-10.7B-v1-Q8_0-GGUF

NaNK

llama-cpp

L3.1-8b-RP-Ink-Q8_0-GGUF

NaNK

llama-cpp

Captain_Eris_Noctis-12B-v0.420-Q8_0-GGUF

NaNK

llama-cpp

MN-Mystic-Rune-12B-Q8_0-GGUF

NaNK

llama-cpp

Moonlit-Shadow-12B-Q8_0-GGUF

Ransss/Moonlit-Shadow-12B-Q80-GGUF This model was converted to GGUF format from `Vortex5/Moonlit-Shadow-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