Microsoft · First MLX build 10 Jun 2025
bitnet-b1.58-2B-4T
MLX
Text mit
A 1.1B parameter text generation model from Microsoft, with 4 MLX builds, from 6-bit to 8-bit.
- Parameters
- 1.1B From Hugging Face
- Quantisation
- 8-bit bitnet-b1.58-2B-4T
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.2 GB Weights, estimated
- Downloads
- 262 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 8-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/bitnet-b1.58-2B-4T --prompt "Hello"MLX builds
4 on mlx-community| bitnet-b1.58-2B-4T-6bit | 6-bit | 495 MB | 3 GB | 39 |
|---|---|---|---|---|
| bitnet-b1.58-2B-4T-4bit | 4-bit | 631 MB | 3 GB | 163 |
| bitnet-b1.58-2B-4T-8bit | 8-bit | 662 MB | 3 GB | 66 |
| bitnet-b1.58-2B-4T | 8-bit | 1.2 GB | 4 GB | 262 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.