MLX Community · First MLX build 25 Apr 2026
DeepSeek-V4-Pro
MLX
Text
A 1.6T parameter text generation model, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 1.6T From Hugging Face
- Quantisation
- 4-bit DeepSeek-V4-Pro-4bit
- Memory needed
- 992 GB Estimate, unified memory
- Download
- 885 GB Weights, estimated
- Downloads
- 424 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 992 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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/DeepSeek-V4-Pro-4bit --prompt "Hello"MLX builds
3 on mlx-community| DeepSeek-V4-Pro-4bit | 4-bit | 885 GB | 992 GB | 424 |
|---|---|---|---|---|
| DeepSeek-V4-Pro-8bit | 8-bit | 1672 GB | 1871 GB | 189 |
| DeepSeek-V4-Pro-bf16 | bf16 | 6241 GB | 6977 GB | 196 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.