mlx-community/DeepSeek-R1-Distill-Qwen-7B-4bit download history
mlx-community/DeepSeek-R1-Distill-Qwen-7B-4bit is a 7.6B-parameter model model by mlx-community. In the last 30 days it was downloaded 2,939 times (795 in the last 7 days), and 76,673 times in total.
It ranks #16,000 on the Hub by monthly downloads.
It has 25 likes.
It is a quantization of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B.
1 models build on DeepSeek-R1-Distill-Qwen-7B-4bit: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 2,963 times in the last 30 days. See the DeepSeek-R1-Distill-Qwen-7B-4bit galaxy.
Most downloaded derivatives
- gilbertomarcano/DeepSeek-R1-Distill-Qwen-7B-4bit-fused-0.0.2 (quantized), 24 downloads in 30 days
Open mlx-community/DeepSeek-R1-Distill-Qwen-7B-4bit on Hugging Face