-
qwen3.6-27btools thinking
5,938 Pulls 5 Tags Updated 1 month ago
-
qwen3.6-35btools thinking
5,309 Pulls 5 Tags Updated 1 month ago
-
gemma4-26b
Gemma 4 26B MoE quantized by BatiAI. 77 t/s on M4 Max. Requires 24GB+ Mac.
tools thinking3,341 Pulls 6 Tags Updated 1 month ago
-
qwen3.5-9b
Qwen 3.5 9B quantized by BatiAI. 12.5 t/s on 16GB Mac. Best for tool calling.
tools thinking2,950 Pulls 3 Tags Updated 1 month ago
-
gemma4-e2btools thinking
2,770 Pulls 2 Tags Updated 1 month ago
-
gemma4-e4btools thinking
2,693 Pulls 2 Tags Updated 1 month ago
-
gemma4-31btools thinking
871 Pulls 4 Tags Updated 1 month ago
-
minimax-m2.7
710 Pulls 2 Tags Updated 1 month ago
-
qwen3-embeddingembedding 0.6b 4b 8b
173 Pulls 9 Tags Updated 1 month ago
-
kimi-k2.6
144 Pulls 3 Tags Updated 4 weeks ago
-
qwen3-vl-embed-8b
132 Pulls 3 Tags Updated 1 month ago
-
qwen3-vl-embed-2b
121 Pulls 3 Tags Updated 1 month ago
-
qwen3.5-27btools thinking
74 Pulls 1 Tag Updated 1 month ago
-
qwen3.5-35btools thinking
68 Pulls 1 Tag Updated 1 month ago
-
mistral-medium-3.5
62 Pulls 3 Tags Updated 3 weeks ago
-
nemotron3-nano-omni-text
35 Pulls 3 Tags Updated 2 weeks ago
-
granite4.1
27 Pulls 6 Tags Updated 3 weeks ago
-
nemotron3-nano
26 Pulls 3 Tags Updated 3 weeks ago
-
llama4-scout
17 Pulls 6 Tags Updated 2 days ago
-
nemotron3-super
12 Pulls 2 Tags Updated 3 weeks ago
-
fara-7b
11 Pulls 7 Tags Updated yesterday