This model was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B using mlx-lm version 0.4.0. Refer to the original model card for more details on the model.

Use with mlx pip install mlx-lm from mlx_lm import load, generate

model, tokenizer = load("jesusoctavioas/DeepSeek-R1-Distill-Qwen-32B-MLX-Q4") response = generate(model, tokenizer, prompt="hello", verbose=True)

Original model link: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B .

Downloads last month: 4

Safetensors

Model size

5.12B params

Tensor type

F16

U32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jesusoctavioas/DeepSeek-R1-Distill-Qwen-32B-MLX-Q4

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Quantized

(142)

this model