All Supported Models

29681 AI models · 198875 quantization formats tracked

M

Maddoxreed

1 models

SmolLM2-135M-Instruct-Q2_K-GGUF

Unknown 8K ctx
FP16
0GB file 2GB
Q2_0
0GB file 2GB
M

Madhu Sagar123

1 models

math-llama-problemMath-Llama3.5K

Unknown 8K ctx
Q4_K_M
0GB file 2GB
M

Madhusudhan001

1 models

qwen2.5-0.5b-materials-science

0.5B 8K ctx
Q8_0
0.53GB file 2.54GB
M

Madibit

1 models

Qwen2.5-3B-Instruct-GGUF

3B 8K ctx
Q2_0
0.94GB file 2.99GB
Q3_0
1.31GB file 3.36GB
Q4_0
1.69GB file 3.74GB
Q5_0
2.06GB file 4.11GB
Q6_0
2.44GB file 4.49GB
Q8_0
3.19GB file 5.24GB
FP16
6GB file 8.05GB
M

Madras1

1 models

Jade8b-GGUF

8B 8K ctx
Q2_0
2.5GB file 4.63GB
Q3_0
3.5GB file 5.63GB
Q4_0
4.5GB file 6.63GB
Q5_0
5.5GB file 7.63GB
Q6_0
6.5GB file 8.63GB
Q8_0
8.5GB file 10.63GB
M

Madroid

1 models

Qwen1.5-0.5B

0.5B 8K ctx
Q4_0
0.28GB file 2.29GB
M

Maelstrome

2 models

lora-wave-session

2B 8K ctx
Q4_K_M
1.13GB file 3.16GB

lora-wave-session-r32

2B 8K ctx
Q4_K_M
1.13GB file 3.16GB
M

Maft Foundation

1 models

qmd-query-expansion-1.7B-gguf

1.7B 8K ctx
Q4_0
0.96GB file 2.99GB
FP16
3.4GB file 5.43GB
M

Magic Decensored

1 models

Apriel-Nemotron-15b-Thinker-Magic_decensored-v2_MPOA-GGUF

15B 8K ctx
Q3_M
6.56GB file 8.81GB
Q4_K_M
8.44GB file 10.69GB
Q4_NL
8.44GB file 10.69GB
Q5_K_M
10.31GB file 12.56GB
Q6_K
12.19GB file 14.44GB
M

Magiccodingman

23 models

Apriel-1.5-15b-Thinker-unsloth-MagicQuant-Hybrid-GGUF

15B 8K ctx
Q4_0
8.44GB file 10.69GB
Q4_NL
8.44GB file 10.69GB

Apriel-1.5-15b-Thinker-Unsloth-MXFP4-Hybrid-GGUF

1B 8K ctx
Q5_K
0.69GB file 2.71GB

Granite-4.0-H-1B-Unsloth-MXFP4-Hybrid-GGUF

1B 8K ctx
Q8_0
1.06GB file 3.08GB

Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF

Unknown 8K ctx
Q6_0
0GB file 2GB

Granite-4.0-H-350M-Unsloth-MXFP4-Hybrid-GGUF

Unknown 8K ctx
Q6_0
0GB file 2GB
Q6_K
0GB file 2GB

Qwen3-30B-A3B-Instruct-2507-unsloth-MagicQuant-Hybrid-GGUF

30B 8K ctx
Q4_0
16.88GB file 19.37GB
Q4_NL
16.88GB file 19.37GB
Q5_K
20.63GB file 23.12GB

Qwen3-30B-A3B-Thinking-2507-unsloth-MagicQuant-Hybrid-GGUF

30B 8K ctx
Q4_0
16.88GB file 19.37GB
Q5_0
20.63GB file 23.12GB
Q5_K
20.63GB file 23.12GB
Q8_0
31.88GB file 34.37GB

Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF

4B 8K ctx
Q4_K
2.25GB file 4.32GB
Q4_K_M
2.25GB file 4.32GB
Q5_K
2.75GB file 4.82GB
Q5_K_M
2.75GB file 4.82GB
Q6_K
3.25GB file 5.32GB
FP4
4GB file 6.07GB
Q8_0
4.25GB file 6.32GB

Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF

4B 8K ctx
Q4_0
2.25GB file 4.32GB
Q4_NL
2.25GB file 4.32GB
Q5_0
2.75GB file 4.82GB
Q6_0
3.25GB file 5.32GB

Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-v2-GGUF

4B 8K ctx
Q2_S
1.25GB file 3.32GB
Q2_XXS
1.25GB file 3.32GB
Q3_S
1.75GB file 3.82GB
Q3_XXS
1.75GB file 3.82GB
Q4_K_M
2.25GB file 4.32GB
Q4_K_S
2.25GB file 4.32GB
Q4_XS
2.25GB file 4.32GB
Q5_K_1
2.75GB file 4.82GB
Q6_K
3.25GB file 5.32GB
Q6_K_1
3.25GB file 5.32GB
Q8_0
4.25GB file 6.32GB

Qwen3-4B-Instruct-2507-Unsloth-MXFP4-Hybrid-GGUF

4B 8K ctx
Q6_K
3.25GB file 5.32GB

Qwen3-4B-Thinking-2507-MXFP4-Hybrid-GGUF

4B 8K ctx
Q6_K
3.25GB file 5.32GB

Qwen3-4B-Thinking-2507-Unsloth-MagicQuant-Hybrid-GGUF

4B 8K ctx
Q4_0
2.25GB file 4.32GB
Q4_K_M
2.25GB file 4.32GB
Q4_NL
2.25GB file 4.32GB
Q5_0
2.75GB file 4.82GB
Q5_K
2.75GB file 4.82GB
Q6_0
3.25GB file 5.32GB

Qwen3-4B-Thinking-2507-Unsloth-MXFP4-Hybrid-GGUF

4B 8K ctx
Q6_K
3.25GB file 5.32GB

Qwen3-VL-32B-Thinking-Unsloth-MXFP4-Hybrid-GGUF

32B 8K ctx
Q6_K
26GB file 28.52GB

Qwen3-VL-8B-Instruct-Unsloth-MXFP4-Hybrid-GGUF

8B 8K ctx
Q6_K
6.5GB file 8.63GB

Qwen3-VL-8B-Thinking-Unsloth-MXFP4-Hybrid-GGUF

8B 8K ctx
Q6_K
6.5GB file 8.63GB
Q8_0
8.5GB file 10.63GB

Qwen3.6-27B-MagicQuant-MTP-GGUF

27B 8K ctx
Q2_M
8.44GB file 10.88GB
Q2_S
8.44GB file 10.88GB
Q2_XXS
8.44GB file 10.88GB
Q3_M_1
11.81GB file 14.25GB
Q3_S
11.81GB file 14.25GB
Q3_XXS
11.81GB file 14.25GB
Q4_NL
15.19GB file 17.63GB
Q4_XS
15.19GB file 17.63GB
Q5_K_S
18.56GB file 21GB
Q6_K_1
21.94GB file 24.38GB
Q6_K_2
21.94GB file 24.38GB
Q6_K_3
21.94GB file 24.38GB
BF16
54GB file 56.44GB

Qwen3.6-27B-Uncensored-MagicQuant-MTP-GGUF

27B 8K ctx
Q2_M
8.44GB file 10.88GB
Q2_S
8.44GB file 10.88GB
Q2_XXS
8.44GB file 10.88GB
Q3_M_1
11.81GB file 14.25GB
Q3_S
11.81GB file 14.25GB
Q3_XXS
11.81GB file 14.25GB
Q4_NL
15.19GB file 17.63GB
Q4_XS
15.19GB file 17.63GB
Q5_K_S
18.56GB file 21GB
Q6_K_1
21.94GB file 24.38GB
Q6_K_3
21.94GB file 24.38GB
BF16
54GB file 56.44GB

Qwen3.6-35B-A3B-MagicQuant-GGUF

35B 8K ctx
Q2_XXS
10.94GB file 13.51GB
Q3_M_1
15.31GB file 17.88GB
Q4_K_M
19.69GB file 22.26GB
Q4_NL
19.69GB file 22.26GB
Q5_K_1
24.06GB file 26.63GB
Q5_K_S
24.06GB file 26.63GB
Q6_K_1
28.44GB file 31.01GB
Q8_0
37.19GB file 39.76GB
BF16
70GB file 72.57GB

Qwen3.6-35B-A3B-Uncensored-MagicQuant-GGUF

35B 8K ctx
Q2_XXS
10.94GB file 13.51GB
Q3_M_1
15.31GB file 17.88GB
Q3_S
15.31GB file 17.88GB
Q4_K_M
19.69GB file 22.26GB
Q4_NL
19.69GB file 22.26GB
Q5_K_1
24.06GB file 26.63GB
Q5_K_S
24.06GB file 26.63GB
Q6_K_1
28.44GB file 31.01GB
Q8_0
37.19GB file 39.76GB
BF16
70GB file 72.57GB

Seed-OSS-36B-Instruct-unsloth-MagicQuant-Hybrid-GGUF

36B 8K ctx
Q4_0
20.25GB file 22.84GB
Q5_0
24.75GB file 27.34GB
Q6_0
29.25GB file 31.84GB
FP4
36GB file 38.59GB
Q8_0
38.25GB file 40.84GB

Seed-OSS-36B-Instruct-Unsloth-MXFP4-Hybrid-GGUF

36B 8K ctx
Q6_K
29.25GB file 31.84GB
FP4
36GB file 38.59GB