mlx-community/Qwen3.8-27B-MTP-8bit

Quantization vs Qwen/Qwen3.8-27B. mlx-community/Qwen3.8-27B-MTP-8bit is a quantized version of the other (U32/BF16).

1 derivatives checked

• t0rr3sp3dr0/Qwen3.8-27B-MLX-MTP-8bit: Partial fine-tune (fewer layers)

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse