All Supported Models

29681 AI models · 198875 quantization formats tracked

M

Marshmallow626

1 models

gemma-4-E4B-it-OBLITERATED

4B 8K ctx
Q4_K_M
2.25GB file 4.32GB
Q5_K_M
2.75GB file 4.82GB
Q8_0
4.25GB file 6.32GB
M

Marsupial A I

12 models

Big-Tiger-Gemma-27B-v1_iMatrix_GGUF

27B 8K ctx
Q2_0
8.44GB file 10.88GB
Q3_0
11.81GB file 14.25GB
Q4_0
15.19GB file 17.63GB
Q5_0
18.56GB file 21GB
Q6_0
21.94GB file 24.38GB
FP16
54GB file 56.44GB

Fireplace-34b_iMatrix_GGUF

34B 8K ctx
Q2_0
10.63GB file 13.19GB
Q3_0
14.88GB file 17.44GB
Q4_0
19.13GB file 21.69GB
Q5_0
23.38GB file 25.94GB
Q6_0
27.63GB file 30.19GB
Q8_0
36.13GB file 38.69GB
FP16
68GB file 70.56GB

Llama-3.1-Nemotron-70B-Instruct_iMat_GGUF

70B 8K ctx
Q2_0
21.88GB file 25.03GB
Q3_0
30.63GB file 33.78GB
Q4_0
39.38GB file 42.53GB
Q5_0
48.13GB file 51.28GB
Q6_0
56.88GB file 60.03GB
FP16
140GB file 143.15GB

Magnum-12b-v2_iMatrix_GGUF

12B 8K ctx
Q2_0
3.75GB file 5.95GB
Q3_0
5.25GB file 7.45GB
Q4_0
6.75GB file 8.95GB
Q5_0
8.25GB file 10.45GB
Q6_0
9.75GB file 11.95GB
FP16
24GB file 26.2GB

MG-FinalMix-72B_iMatrix_GGUF

72B 8K ctx
Q2_0
22.5GB file 25.68GB
Q3_0
31.5GB file 34.68GB
Q4_0
40.5GB file 43.68GB
Q5_0
49.5GB file 52.68GB
Q6_0
58.5GB file 61.68GB
FP16
144GB file 147.18GB

Monstral-123B_iMat_GGUF

123B 8K ctx
Q2_0
38.44GB file 42.46GB
Q3_0
53.81GB file 57.83GB
Q4_0
69.19GB file 73.21GB
FP16
246GB file 250.02GB

Monstral-123B-v2_GGUF

123B 8K ctx
Q2_0
38.44GB file 42.46GB
Q3_0
53.81GB file 57.83GB
Q4_0
69.19GB file 73.21GB
FP16
246GB file 250.02GB

Phi-3-mini-128k-instruct_iMatrix_GGUF

3.8B 8K ctx
Q2_0
1.19GB file 3.25GB
Q3_0
1.66GB file 3.72GB
Q4_0
2.14GB file 4.2GB
Q5_0
2.61GB file 4.67GB
Q6_0
3.09GB file 5.15GB
Q8_0
4.04GB file 6.1GB
FP16
7.6GB file 9.66GB

Pygmalion-2-13b_iMatrix_GGUF

13B 8K ctx
Q2_0
4.06GB file 6.27GB
Q3_0
5.69GB file 7.9GB
Q4_0
7.31GB file 9.52GB
Q5_0
8.94GB file 11.15GB
Q6_0
10.56GB file 12.77GB
Q8_0
13.81GB file 16.02GB
FP16
26GB file 28.21GB

Qwen1.5-32B_iMatrix_GGUF

32B 8K ctx
Q2_0
10GB file 12.52GB
Q3_0
14GB file 16.52GB
Q4_0
18GB file 20.52GB
Q5_0
22GB file 24.52GB
Q6_0
26GB file 28.52GB
Q8_0
34GB file 36.52GB
FP16
64GB file 66.52GB

Qwen1.5-32B-Chat_iMatrix_GGUF

32B 8K ctx
Q2_0
10GB file 12.52GB
Q3_0
14GB file 16.52GB
Q4_0
18GB file 20.52GB
Q1_0
32GB file 34.52GB
FP16
64GB file 66.52GB

Yi-9B-200K_iMatrix_GGUF

9B 8K ctx
Q2_0
2.81GB file 4.96GB
Q3_0
3.94GB file 6.09GB
Q4_0
5.06GB file 7.21GB
FP16
18GB file 20.15GB
M

Martin T Studio

1 models

Qwen3-4B-Instruct-2507-heretic-gguf

4B 8K ctx
Q3_0
1.75GB file 3.82GB
Q4_0
2.25GB file 4.32GB
Q8_0
4.25GB file 6.32GB
M

Martintomov

16 models

gemma-2-27b-it-Q8_0-GGUF

27B 8K ctx
Q8_0
28.69GB file 31.13GB

gemma-2-2b-Q5_K_M-GGUF

2B 8K ctx
Q5_0
1.38GB file 3.41GB
FP16
4GB file 6.03GB

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

9B 8K ctx
Q8_0
9.56GB file 11.71GB

gemma-2-9b-Q4_K_M-GGUF

9B 8K ctx
Q4_0
5.06GB file 7.21GB
FP16
18GB file 20.15GB

h2o-danube-1.8b-chat-Q8_0-GGUF

1.8B 8K ctx
Q8_0
1.91GB file 3.94GB

h2o-danube3-4b-base-Q8_0-GGUF

4B 8K ctx
Q8_0
4.25GB file 6.32GB

h2o-danube3-4b-chat-Q8_0-GGUF

4B 8K ctx
Q8_0
4.25GB file 6.32GB

Meta-Llama-3-8B-Alternate-Tokenizer-Q4_K_S-GGUF

8B 8K ctx
Q4_0
4.5GB file 6.63GB
FP16
16GB file 18.13GB

Meta-Llama-Guard-2-8B-Q8_0-GGUF

8B 8K ctx
Q8_0
8.5GB file 10.63GB

NuminaMath-7B-TIR-Q4_K_M-GGUF

7B 8K ctx
Q4_0
3.94GB file 6.05GB
FP16
14GB file 16.11GB

NuminaMath-7B-TIR-Q8_0-GGUF

7B 8K ctx
Q8_0
7.44GB file 9.55GB

Phi-3-medium-128k-instruct-Q4_K_S-GGUF

3.8B 8K ctx
Q4_0
2.14GB file 4.2GB
FP16
7.6GB file 9.66GB

Qwen1.5-14B-Chat-Q4_K_M-GGUF

14B 8K ctx
Q4_0
7.88GB file 10.11GB
FP16
28GB file 30.23GB

Qwen1.5-32B-Chat-Q4_K_M-GGUF

32B 8K ctx
Q4_0
18GB file 20.52GB
FP16
64GB file 66.52GB

Qwen2-0.5B-Instruct-Q4_K_M-GGUF

0.5B 8K ctx
Q4_0
0.28GB file 2.29GB
FP16
1GB file 3.01GB

Qwen2-7B-Instruct-Q4_K_M-GGUF

7B 8K ctx
Q4_0
3.94GB file 6.05GB
FP16
14GB file 16.11GB
M

Martyn

2 models

mixtral-megamerge-dare-8x7b-v1-GGUF

7B 8K ctx
Q4_K_M
3.94GB file 6.05GB
Q4_K_S
3.94GB file 6.05GB
Q6_K
5.69GB file 7.8GB
Q8_0
7.44GB file 9.55GB

mixtral-megamerge-dare-8x7b-v2-GGUF

7B 8K ctx
Q4_K_M
3.94GB file 6.05GB
Q4_K_S
3.94GB file 6.05GB
Q6_K
5.69GB file 7.8GB
Q8_0
7.44GB file 9.55GB
M

Marwanahmed99

1 models

medical-Q8_0-GGUF

1B 8K ctx
Q8_0
1.06GB file 3.08GB
M

Marz Lars

2 models

ERNIE-4.5-0.3B-PT-Q3_K_M-GGUF

0.3B 8K ctx
Q3_0
0.13GB file 2.13GB
FP16
0.6GB file 2.6GB

ERNIE-4.5-0.3B-PT-Q4_K_M-GGUF

0.3B 8K ctx
Q4_0
0.17GB file 2.17GB
FP16
0.6GB file 2.6GB
M

Mashima

9 models

EZO-Common-9B-gemma-2-it-Q8_0-GGUF

9B 8K ctx
Q8_0
9.56GB file 11.71GB

EZO-Humanities-9B-gemma-2-it-Q8_0-GGUF

9B 8K ctx
Q8_0
9.56GB file 11.71GB

gemma-2-27b-it-Q4_K_M-GGUF

27B 8K ctx
Q4_0
15.19GB file 17.63GB
FP16
54GB file 56.44GB

gemma-2-9b-it-Q6_K-GGUF

9B 8K ctx
Q6_0
7.31GB file 9.46GB
FP16
18GB file 20.15GB

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

9B 8K ctx
Q8_0
9.56GB file 11.71GB

Qwen2.5-14B-Instruct-Q4_0-GGUF

14B 8K ctx
Q4_0
7.88GB file 10.11GB

Qwen2.5-14B-Instruct-Q6_K-GGUF

14B 8K ctx
Q6_0
11.38GB file 13.61GB
FP16
28GB file 30.23GB

Qwen2.5-14B-Instruct-Q8_0-GGUF

14B 8K ctx
Q8_0
14.88GB file 17.11GB

Qwen2.5-7B-Instruct-Q8_0-GGUF

7B 8K ctx
Q8_0
7.44GB file 9.55GB
M

Massimilianowosz

1 models

gemma-3-1b-it-ita-gguf

1B 8K ctx
Q4_K_M
0.56GB file 2.58GB
M

Massiv Dash

4 models

Qwen3-1.7B-heretic-Q8_0-GGUF

1.7B 8K ctx
Q8_0
1.81GB file 3.84GB

Qwen3-4B-heretic-Q8_0-GGUF

4B 8K ctx
Q8_0
4.25GB file 6.32GB

Qwen3-4B-Instruct-2507-heretic-Q6_K-GGUF

4B 8K ctx
Q6_0
3.25GB file 5.32GB
FP16
8GB file 10.07GB

Qwen3-4B-Instruct-2507-heretic-Q8_0-GGUF

4B 8K ctx
Q8_0
4.25GB file 6.32GB