lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bit

Quantization vs Qwen/Qwen3-4B-Thinking-2507. lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bit is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse