nex-agi · First MLX build 8 Jun 2026
Nex-N2-mini
MLX
Text apache-2.0
A 35B parameter text generation model from nex-agi, with 7 MLX builds, from 4-bit to 8-bit.
- Parameters
- 35B From Hugging Face
- Quantisation
- 4-bit Nex-N2-mini-nvfp4
- Memory needed
- 25 GB Estimate, unified memory
- Download
- 20.4 GB Weights, estimated
- Downloads
- 43 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 7 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 25 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/Nex-N2-mini-nvfp4 --prompt "Hello"MLX builds
7 on mlx-community| Nex-N2-mini-nvfp4 | 4-bit | 20.4 GB | 25 GB | 43 |
|---|---|---|---|---|
| Nex-N2-mini-4bit | 4-bit | 20.4 GB | 25 GB | 29 |
| Nex-N2-mini-5bit | 5-bit | 24.7 GB | 30 GB | 22 |
| Nex-N2-mini-mlx-optiq-static-mixed-3_6bits | 6-bit | 28.2 GB | 34 GB | 27 |
| Nex-N2-mini-6bit | 6-bit | 29.1 GB | 35 GB | 30 |
| Nex-N2-mini-mxfp8 | MXFP8 | 37.7 GB | 45 GB | 42 |
| Nex-N2-mini-8bit | 8-bit | 37.7 GB | 45 GB | 28 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.