MLX Community · First MLX build 29 Aug 2024
Minitron-4B-Base
MLX
nvidia-open-model-license
A 4.2B parameter model, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 4.2B From Hugging Face
- Quantisation
- Unstated Minitron-4B-Base
- Memory needed
- 12 GB Estimate, unified memory
- Download
- 8.4 GB Weights, estimated
- Downloads
- 15 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 12 GB at Unstated
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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Minitron-4B-BaseMLX builds
3 on mlx-community| Minitron-4B-Base-4bit | 4-bit | 2.4 GB | 5 GB | 12 |
|---|---|---|---|---|
| Minitron-4B-Base-8bit | 8-bit | 4.5 GB | 7 GB | 11 |
| Minitron-4B-Base | Unstated | 8.4 GB | 12 GB | 15 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.