All Supported Models

29681 AI models · 198875 quantization formats tracked

M

Michaelw9999

1 models

Nemotron-Cascade-2-30B-A3B-NVFP4-GGUF

30B 8K ctx
FP4
30GB file 32.49GB
M

Michelinolinolino

2 models

gemma4-4b-sci

4B 8K ctx
FP16
8GB file 10.07GB

gemma4-4b-tikz

4B 8K ctx
FP16
8GB file 10.07GB
M

Michelkao

1 models

Ollama-3.2-GGUF

3B 8K ctx
Q4_K_M
1.69GB file 3.74GB
Q5_K_M
2.06GB file 4.11GB
Q8_0
3.19GB file 5.24GB
M

Michiel Buisman

3 models

granite-4.0-h-micro-dutch-calibrated-gguf

Unknown 8K ctx
Q4_0
0GB file 2GB
FP16
0GB file 2GB

granite-4.0-h-small-dutch-calibrated-gguf

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

granite-4.0-micro-dutch-calibrated-gguf

Unknown 8K ctx
Q5_K_NL
0GB file 2GB
Q6_K_NL
0GB file 2GB
Q4_K_NL
0GB file 2GB
M

Mickjosh

1 models

Llama-3.2-3B-Instruct-Q4_K_M-GGUF

3B 8K ctx
Q4_0
1.69GB file 3.74GB
FP16
6GB file 8.05GB
M

Mickymultani

1 models

Cree-Llama-3.3-70B

70B 8K ctx
Q4_K_M
39.38GB file 42.53GB
M

Midoriinko

2 models

magnum-v4-123b-jp-imatrix

123B 8K ctx
Q3_XXS
53.81GB file 57.83GB
Q3_S
53.81GB file 57.83GB
Q3_M
53.81GB file 57.83GB

Monstral-123B-jp-gguf

123B 8K ctx
Q3_M
53.81GB file 57.83GB
Q3_XXS
53.81GB file 57.83GB
Q4_K_M
69.19GB file 73.21GB
M

Midorin Linux

1 models

gpt-oss-20b-Coding-Distill-GGUF

20B 8K ctx
FP4
20GB file 22.33GB
M

Migarcoes

19 models

deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B

1.5B 8K ctx
Q4_K_M
0.84GB file 2.86GB

deepseek-ai-ESFT-gate-code-lite

Unknown 8K ctx
Q4_K_M
0GB file 2GB

EleutherAI-pythia-1b

1B 8K ctx
Q4_K_M
0.56GB file 2.58GB

HuggingFaceTB-SmolLM2-1.7B-Instruct

1.7B 8K ctx
Q4_K_M
0.96GB file 2.99GB

meta-llama-Llama-3.2-1B

1B 8K ctx
Q4_K_M
0.56GB file 2.58GB

Qwen-Qwen2.5-1.5B-Instruct

1.5B 8K ctx
Q4_K_M
0.84GB file 2.86GB

Qwen-Qwen2.5-Coder-0.5B-Instruct

0.5B 8K ctx
Q4_K_M
0.28GB file 2.29GB

Qwen-Qwen2.5-Coder-1.5B-Instruct

1.5B 8K ctx
Q4_K_M
0.84GB file 2.86GB

Qwen-Qwen3-Embedding-0.6B

0.6B 8K ctx
Q4_K_M
0.34GB file 2.35GB

Qwen-Qwen3.5-0.8B-Base

0.8B 8K ctx
Q4_K_M
0.45GB file 2.46GB

Qwen-Qwen3.5-2B-Base

2B 8K ctx
Q4_K_M
1.13GB file 3.16GB

Qwen-Qwen3.5-4B-Base

4B 8K ctx
Q4_K_M
2.25GB file 4.32GB

Qwen3.5-0.8B

0.8B 8K ctx
Q4_K_M
0.45GB file 2.46GB
Q8_0
0.85GB file 2.86GB

Qwen3.5-2B

2B 8K ctx
Q4_K_M
1.13GB file 3.16GB
Q8_0
2.13GB file 4.16GB

Qwen3.5-4B

4B 8K ctx
Q4_K_M
2.25GB file 4.32GB
Q8_0
4.25GB file 6.32GB

Qwen3.5-9B

9B 8K ctx
Q4_K_M
5.06GB file 7.21GB
Q8_0
9.56GB file 11.71GB

TinyLlama-TinyLlama_v1.1_chinese

Unknown 8K ctx
Q4_K_M
0GB file 2GB

TinyLlama-TinyLlama_v1.1_math_code

Unknown 8K ctx
Q4_K_M
0GB file 2GB

TinyLlama-TinyLlama-1.1B-Chat-v1.0

1.1B 8K ctx
Q4_K_M
0.62GB file 2.64GB
M

Migs N9

1 models

SmolLM2-360M-Instruct-Mem-Cat

Unknown 8K ctx
Q8_0
0GB file 2GB