MLX Community · First MLX build 3 Dec 2025
Ministral-3-8B-Reasoning-2512
MLX
apache-2.0
A 8.9B parameter model, with 5 MLX builds, from bf16 to 5-bit.
- Parameters
- 8.9B From Hugging Face
- Quantisation
- 4-bit Ministral-3-8B-Reasoning-2512-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 234 This build, last 30 days
- Task
- —
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/Ministral-3-8B-Reasoning-2512-4bitMLX builds
5 on mlx-community| Ministral-3-8B-Reasoning-2512-bf16 | bf16 | 17.8 GB | 22 GB | 34 |
|---|---|---|---|---|
| Ministral-3-8B-Reasoning-2512-4bit | 4-bit | — | — | 234 |
| Ministral-3-8B-Reasoning-2512-8bit | 8-bit | — | — | 68 |
| Ministral-3-8B-Reasoning-2512-6bit | 6-bit | — | — | 58 |
| Ministral-3-8B-Reasoning-2512-5bit | 5-bit | — | — | 43 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.