MLX Community · First MLX build 11 Aug 2026
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
MLX
Text openmdw-1.1
A 32B parameter text generation model, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 32B From Hugging Face
- Quantisation
- 4-bit NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit
- Memory needed
- 22 GB Estimate, unified memory
- Download
- 17.8 GB Weights, estimated
- Downloads
- 2.7K 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 22 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/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit --prompt "Hello"MLX builds
4 on mlx-community| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit | 4-bit | 17.8 GB | 22 GB | 2.7K |
|---|---|---|---|---|
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp4 | MXFP4 | 17.8 GB | 22 GB | 550 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp8 | MXFP8 | 33.6 GB | 40 GB | 962 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-8bit | 8-bit | 33.6 GB | 40 GB | 449 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.