This is a 6bit quant of deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Probably the sweet spot for running o1 at home :)

Downloads last month: 111

Safetensors

Model size

6.66B params

Tensor type

FP16

U32

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for nisten/deepseek-r1-qwen32b-mlx-6bit

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-Coder-32B

Quantized

(18)

this model