lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit

Quantization vs deepseek-ai/DeepSeek-R1-0528-Qwen3-8B. lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit is a quantized version of the other (U32/BF16).

1 derivatives checked

• introvoyz041/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit-mlx-4Bit: Same weights, repacked

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

On the Hub · Downloads on Model Pulse