Mistral AI · First MLX build 3 Dec 2025
Ministral-3-14B-Instruct-2512
MLX
Text apache-2.0
A 14B parameter text generation model from Mistral AI, with 2 MLX builds at MXFP4.
- Parameters
- 14B From Hugging Face
- Quantisation
- MXFP4 mistralai_Ministral-3-14B-Instruct-2512-MLX-MXFP4
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.6 GB Weights, estimated
- Downloads
- 995 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 11 GB at MXFP4
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/mistralai_Ministral-3-14B-Instruct-2512-MLX-MXFP4 --prompt "Hello"MLX builds
2 on mlx-community| mistralai_Ministral-3-14B-Instruct-2512-MLX-MXFP4 | MXFP4 | 7.6 GB | 11 GB | 995 |
|---|---|---|---|---|
| Ministral-3-14B-Instruct-2512 | Unstated | 27.0 GB | 33 GB | 148 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.