Nanbeige · First MLX build 11 Feb 2026
Nanbeige4.1-3B
MLX
Text apache-2.0
A 3.9B parameter text generation model from Nanbeige, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 3.9B From Hugging Face
- Quantisation
- 8-bit Nanbeige4.1-3B-8bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.2 GB Weights, estimated
- Downloads
- 1.3K 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 7 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/Nanbeige4.1-3B-8bit --prompt "Hello"MLX builds
3 on mlx-community| Nanbeige4.1-3B-4bit | 4-bit | 2.2 GB | 5 GB | 76 |
|---|---|---|---|---|
| Nanbeige4.1-3B-8bit | 8-bit | 4.2 GB | 7 GB | 1.3K |
| Nanbeige4.1-3B-bf16 | bf16 | 7.9 GB | 11 GB | 58 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.