turboderp

112 models • 4 total models in database
Sort by:

Cat-Llama-3-70B-instruct

NaNK
llama
8,519
53

Llama-3-8B-Instruct-exl2

NaNK
1,746
42

gemma-2-9b-it-exl2

NaNK
874
8

GLM 4.6 Exl3 2.33bpw Opt

This is just a quick mix of the 2.25 bpw quant with attention, dense layers and shared experts in 4.0 bpw.

NaNK
license:mit
328
4

Devstral-2-123B-Instruct-2512-exl3

NaNK
251
7

Mistral-Small-3.1-24B-Instruct-2503-exl3

NaNK
license:apache-2.0
174
2

GLM-4.5-Air-exl3

NaNK
license:mit
154
18

Mistral-Large-Instruct-2411-exl3

NaNK
122
9

Qwen3-Next-80B-A3B-Instruct-exl3

⚠️ Requires ExLlamaV3 v0.0.7 (or v0.0.6 `dev` branch) 2.00 bits per weight 3.00 bits per weight 4.00 bits per weight 5.00 bits per weight 2.08 bits per weight 2.27 bits per weight 2.78 bits per weight 3.14 bits per weight 3.53 bits per weight 4.06 bits per weight 4.51 bits per weight

NaNK
license:apache-2.0
91
24

Qwen3-Next-80B-A3B-Thinking-exl3

⚠️ Requires ExLlamaV3 v0.0.7 (or v0.0.6 `dev` branch) 2.00 bits per weight 3.00 bits per weight 4.00 bits per weight 5.00 bits per weight 6.00 bits per weight 2.08 bits per weight 2.27 bits per weight 2.78 bits per weight 3.14 bits per weight 3.53 bits per weight 4.06 bits per weight 4.51 bits per weight

NaNK
license:apache-2.0
89
6

Qwama-0.5B-Instruct

NaNK
license:apache-2.0
56
17

EXAONE-4.0-32B-exl3

2.00 bits per weight 2.50 bits per weight 3.00 bits per weight 3.50 bits per weight 4.00 bits per weight 5.00 bits per weight 6.00 bits per weight 8.00 bits per weight / H8

NaNK
56
6

Qwen3-8B-exl3

NaNK
license:apache-2.0
44
5

ERNIE-4.5-300B-A47B-Base-PT-exl3

NaNK
license:apache-2.0
42
0

gemma-2-27b-it-exl2

NaNK
36
25

gemma-3-27b-it-exl3

NaNK
33
7

Qwen3-30B-A3B-exl3

NaNK
license:apache-2.0
33
6

ERNIE-4.5-300B-A47B-PT-exl3

NaNK
license:apache-2.0
33
3

Mistral-Large-Instruct-2407-123B-exl2

NaNK
29
17

SmolLM3-3B-exl3

2.00 bits per weight 2.50 bits per weight 3.00 bits per weight 3.50 bits per weight 4.00 bits per weight 5.00 bits per weight 6.00 bits per weight 8.00 bits per weight / H8

NaNK
license:apache-2.0
29
0

Qwen3-32B-exl3

NaNK
license:apache-2.0
28
18

Llama-3.1-70B-Instruct-exl2

NaNK
license:llama3.1
26
19

Llama-3.1-8B-Instruct-exl2

NaNK
license:llama3.1
24
14

Grok-3-reasoning-gemma3-12B-distilled-HF-exl3

EXL3 quants of Grok-3-reasoning-gemma3-12B-distilled-HF

NaNK
license:apache-2.0
22
0

Llama-3.1-70B-Instruct-exl3

NaNK
base_model:meta-llama/Llama-3.1-70B-Instruct
19
1

MiniMax-M2-exl3

⚠️ Requires ExLlamaV3 v0.0.12 (or v0.0.11 `dev` branch) 2.00 bits per weight 3.00 bits per weight 4.00 bits per weight 2.04 bits per weight 2.27 bits per weight 3.04 bits per weight 3.50 bits per weight 4.03 bits per weight . | KL-div | ppl | HumanEval@1 ---------|--------|-------|------------- 2.00 bpw | 0.400 | 10.92 | 80.5% 2.04 bpw | 0.297 | 10.23 | 87.1% 2.27 bpw | 0.252 | 9.78 | 88.4% 3.00 bpw | 0.141 | 8.99 | 87.8% 3.04 bpw | 0.117 | 8.73 | 87.2% 3.50 bpw | 0.094 | 8.78 | 88.4% 4.00 bpw | 0.087 | 8.58 | 89.6% 4.03 bpw | 0.077 | 8.61 | 87.8% original | - | 8.51 | 87.2%¹

NaNK
license:mit
18
5

Apertus-70B-Instruct-2509-exl3

2.00 bits per weight 2.50 bits per weight 3.00 bits per weight 3.50 bits per weight 4.00 bits per weight 5.00 bits per weight 6.00 bits per weight . | MMLU | 95% CI ----------|--------------|------------ 2.0 bpw | 58.90% | +/- 1.50% 2.5 bpw | 64.20% | +/- 1.46% 3.0 bpw | 67.00% | +/- 1.43% 3.5 bpw | 67.70% | +/- 1.43% 4.0 bpw | 69.40% | +/- 1.40% 5.0 bpw | 70.30% | +/- 1.39% 6.0 bpw | 69.60% | +/- 1.40%

NaNK
license:apache-2.0
17
1

Qwen2.5-VL-7B-Instruct-exl2

NaNK
license:apache-2.0
16
5

c4ai-command-r7b-12-2024-exl3

2.00 bits per weight 2.50 bits per weight 3.00 bits per weight 4.00 bits per weight 5.00 bits per weight 6.00 bits per weight 8.00 bits per weight / H8

NaNK
license:cc-by-nc-4.0
15
1

c4ai-command-r-08-2024-exl3

2.00 bits per weight 2.50 bits per weight 3.00 bits per weight 4.00 bits per weight 5.00 bits per weight 6.00 bits per weight 8.00 bits per weight / H8

NaNK
license:cc-by-nc-4.0
13
5

Qwen3-VL-235B-A22B-Thinking-exl3

NaNK
license:apache-2.0
13
1

Mistral-7B-Instruct-v0.3-exl3

NaNK
license:apache-2.0
13
1

Mistral-Nemo-Instruct-12B-exl2

NaNK
license:apache-2.0
12
21

GLM-4.6V-exl3

NaNK
license:mit
12
4

command-r-plus-103B-exl2

NaNK
11
34

Mixtral-8x7B-exl2

NaNK
11
14

Llama-3.1-8B-Instruct-exl3

NaNK
base_model:meta-llama/Llama-3.1-8B-Instruct
11
2

Llama-3.2-1B-Instruct-exl3

NaNK
base_model:meta-llama/Llama-3.2-1B-Instruct
9
1

Qwen2.5-7B-Instruct-exl3

NaNK
license:apache-2.0
9
1

gemma-3-27b-it-exl2

NaNK
8
15

Mistral-7B-instruct-v0.3-exl2

NaNK
license:apache-2.0
8
2

CodeLlama-34B-instruct-exl2

NaNK
7
8

Apertus-8B-Instruct-2509-exl3

2.00 bits per weight 2.50 bits per weight 3.00 bits per weight 3.50 bits per weight 4.00 bits per weight 5.00 bits per weight 6.00 bits per weight 8.00 bits per weight / H8

NaNK
license:apache-2.0
7
1

dbrx-instruct-exl2

6
27

Llama-3.3-Nemotron-Super-49B-v1-exl3

NaNK
base_model:nvidia/Llama-3_3-Nemotron-Super-49B-v1
6
17

Llama2-7B-chat-exl2

NaNK
6
3

Llama-3.2-3B-Instruct-exl2

NaNK
license:llama3.2
6
2

Qwen3-0.6B-exl3

NaNK
license:apache-2.0
6
2

Mixtral-8x7B-instruct-exl2

NaNK
5
73

turbcat-instruct-72b

NaNK
5
30

command-r-v01-35B-exl2

NaNK
5
18

Llama-3-70B-exl2

NaNK
5
10

gemma-3-12b-it-exl2

NaNK
5
3

Qwama-0.5B-Instruct-exl2

NaNK
5
0

Phi-3-mini-128k-instruct-exl2

4
6

turbcat-instruct-72b-exl2

NaNK
4
6

Qwen3-235B-A22B-exl3

2.00 bits per weight 2.25 bits per weight 2.50 bits per weight 3.00 bits per weight

NaNK
license:apache-2.0
4
5

Mistral-7B-instruct-exl2

NaNK
3
15

gemma-4-26B-A4B-it-exl3

NaNK
license:apache-2.0
3
5

gemma-4-26B-A4B-exl3

NaNK
license:apache-2.0
3
5

llama3-turbcat-instruct-8b-exl2

NaNK
license:llama3
3
5

Mistral-Nemo-Base-12B-exl2

NaNK
license:apache-2.0
3
3

dots.llm1.inst-exl3

NaNK
license:mit
3
3

CodeLlama-13B-instruct-exl2

NaNK
3
2

Qwen2.5-14B-Instruct-exl3

NaNK
license:apache-2.0
3
2

c4ai-command-r-plus-08-2024-exl3

2.07 bits per weight 2.50 bits per weight 3.00 bits per weight 4.00 bits per weight 5.00 bits per weight

NaNK
license:cc-by-nc-4.0
3
2

OpenLlama-3B-exl2

NaNK
3
1

TinyLlama-1B-32k-exl2

NaNK
3
1

Phi-4-mini-instruct-exl3

NaNK
license:mit
3
1

gemma-2-9b-it-exl3

NaNK
3
1

Llama-3-70B-Instruct-exl2

NaNK
2
51

llama3-turbcat-instruct-8b

NaNK
llama
2
34

Llama2-70B-exl2

NaNK
2
9

pixtral-12b-exl2

NaNK
license:apache-2.0
2
8

Qwen1.5-110B-Chat-exl2

NaNK
2
6

Step-3.5-Flash-exl3

NaNK
license:apache-2.0
2
3

Mistral-Small-3.1-24B-Instruct-2503-exl2

NaNK
license:apache-2.0
2
3

gpt2-exl2

license:mit
2
0

Mixtral-8x7B-Instruct-v0.1-exl3

NaNK
license:apache-2.0
2
0

Llama-3-8B-exl2

NaNK
1
9

Llama2-70B-chat-exl2

NaNK
1
8

TinyLlama-1B-exl2

NaNK
1
7

Llama2-7B-exl2

NaNK
1
3

Cat-Llama-3-70B-instruct-exl2

NaNK
1
3

Llama2-13B-exl2

NaNK
1
2

Gemma-7B-it-exl2

NaNK
1
2

granite-20b-code-instruct-exl2

NaNK
license:apache-2.0
1
2

Qwen3-30B-A3B-exl2

NaNK
license:apache-2.0
1
2

Gemma-7B-exl2

NaNK
1
1

Llama-3.2-3B-exl2

NaNK
license:llama3.2
1
1

StarCoder2-7B-exl2

NaNK
1
0

Mixtral-8x22B-v0.1-exl2

NaNK
0
12

Mixtral-8x22B-Instruct-v0.1-exl2

NaNK
0
11

Smaug-72B-exl2

NaNK
0
7

Qwen3.5-35B-A3B-exl3

NaNK
license:apache-2.0
0
6

Mistral-7B-v0.2-exl2

NaNK
0
5

Qwen2-VL-7B-Instruct-exl2

NaNK
license:apache-2.0
0
5

Llama-3.1-Nemotron-Ultra-253B-v1-exl3

NaNK
base_model:nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
0
5

dbrx-base-exl2

0
4

Qwen3.5-122B-A10B-exl3

NaNK
license:apache-2.0
0
3

Qwen3-VL-30B-A3B-Instruct-exl3

NaNK
license:apache-2.0
0
2

CodeLlama-13B-exl2

NaNK
0
2

Mistral-7B-OpenOrca-exl2

NaNK
0
2

Llama-3.2-1B-Instruct-exl2

NaNK
license:llama3.2
0
2

Qwen3.5-9B-exl3

NaNK
license:apache-2.0
0
1

deepseek-llm-67B-chat-exl2

NaNK
0
1

Goliath-120B-exl2

NaNK
0
1

Orion-14B-chat-exl2

NaNK
0
1

gpt2-medium-exl2

license:mit
0
1

Llama-3.2-1B-exl2

NaNK
license:llama3.2
0
1

Qwen2-VL-2B-Instruct-exl2

NaNK
license:apache-2.0
0
1

Qwen2-VL-72B-Instruct-exl2

NaNK
license:apache-2.0
0
1