DeepSeek · First MLX build 29 May 2025
DeepSeek-R1-0528
MLX
Text mit
A 671B parameter text generation model from DeepSeek, with 2 MLX builds, from 3-bit to 5-bit.
- Parameters
- 671B From Hugging Face
- Quantisation
- 3-bit DeepSeek-R1-0528-3bit
- Memory needed
- 331 GB Estimate, unified memory
- Download
- 294 GB Weights, estimated
- Downloads
- 69 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 331 GB at 3-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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/DeepSeek-R1-0528-3bit --prompt "Hello"MLX builds
2 on mlx-community| DeepSeek-R1-0528-3bit | 3-bit | 294 GB | 331 GB | 69 |
|---|---|---|---|---|
| DeepSeek-R1-0528-5bit | 5-bit | 461 GB | 518 GB | 52 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.