MLX Community · First MLX build 18 Aug 2025
Voxtral-Mini-3B-2507
MLX
apache-2.0
A 4.7B parameter model, with one MLX build at bf16.
- Parameters
- 4.7B From Hugging Face
- Quantisation
- bf16 Voxtral-Mini-3B-2507-bf16
- Memory needed
- 13 GB Estimate, unified memory
- Download
- 9.4 GB Weights, estimated
- Downloads
- 917 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 13 GB at bf16
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/Voxtral-Mini-3B-2507-bf16MLX builds
1 on mlx-community| Voxtral-Mini-3B-2507-bf16 | bf16 | 9.4 GB | 13 GB | 917 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.