AlejandroOlmedo/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-8bit-mlx

Quantization vs Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math. AlejandroOlmedo/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-8bit-mlx is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse