ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit

Quantization vs Qwen/Qwen3.8-Flash-Next. ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse