mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit
Quantization vs Qwen/Qwen3-235B-A22B-Instruct-2507. mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit is a quantized version of the other (U32/BF16).
1 derivatives checked
- mlx-community/Qwen3-235B-A22B-Instruct-2507-3bit-DWQ: Partial fine-tune