4-bit Open on Hugging Face
Parameters
671B
Weights (est.)
≈ 378 GB
Mac memory (est.)
512 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/DeepSeek-R1-qm_4_2 --prompt "Hello"
Details
- Base model
- deepseek-ai/DeepSeek-R1 (quantized) · DeepSeek R1 on the radar →
- Vendor
- DeepSeek
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 36 in the last 30 days · 373 all time · 0 likes
- Published
- 2025-03-06 · updated 2025-03-06 (1y ago)
- Tags
- deepseek_v3, custom_code
Other MLX builds of deepseek-ai/DeepSeek-R1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepSeek-R1-2bit | 2-bit | ≈ 210 GB | 256 GB+ | 201 |
| DeepSeek-R1-3bit | 3-bit | ≈ 294 GB | 512 GB+ | 699 |
| DeepSeek-R1-4bit | 4-bit | ≈ 378 GB | 512 GB+ | 1.7K |
| DeepSeek-R1-qm_4_2 (this one) | 4-bit | ≈ 378 GB | 512 GB+ | 36 |
| DeepSeek-R1 | 8-bit | — | — | 53 |