DeepSeek · First MLX build 20 Jan 2025
DeepSeek-R1
MLX
Text mit
A 671B parameter text generation model from DeepSeek, with 5 MLX builds, from 2-bit to 8-bit.
- Parameters
- 671B From Hugging Face
- Quantisation
- 4-bit DeepSeek-R1-4bit
- Memory needed
- 425 GB Estimate, unified memory
- Download
- 378 GB Weights, estimated
- Downloads
- 1.7K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 425 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/DeepSeek-R1-4bitMLX builds
5 on mlx-community| DeepSeek-R1-2bit | 2-bit | 210 GB | 237 GB | 205 |
|---|---|---|---|---|
| DeepSeek-R1-3bit | 3-bit | 294 GB | 331 GB | 722 |
| DeepSeek-R1-4bit | 4-bit | 378 GB | 425 GB | 1.7K |
| DeepSeek-R1-qm_4_2 | 4-bit | 378 GB | 425 GB | 35 |
| DeepSeek-R1 | 8-bit | — | — | 55 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.