mlx-community/DeepSeek-R1-0528-8bit
Text Generation • 671B • Updated
• 55
Big one
-
-
Qwen/Qwen3-235B-A22B-MLX-bf16
Text Generation • 235B • Updated • 101 • 6 -
inferencerlabs/Qwen3-Coder-480B-A35B-Instruct-MLX-8.5bit
Text Generation • 480B • Updated • 504 • 2 -
mlx-community/GLM-5-MXFP4-Q8
Text Generation • 744B • Updated • 3.31k • 1 -
richardyoung/Kimi-K2-Instruct-0905-MLX-5bit
Text Generation • 1T • Updated • 51 -
mlx-community/Kimi-K2-Thinking
Text Generation • 1T • Updated • 40.9k • 17