Parameters
14B
Weights (est.)
≈ 27.0 GB
Mac memory (est.)
48 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Ministral-3-14B-Instruct-2512 --prompt "Hello"
Details
- Base model
- mistralai/Ministral-3-14B-Instruct-2512 (quantized)
- Vendor
- Mistral
- Task
- Text generation
- Quantisation
- Not stated
- Licence
- apache-2.0
- Downloads
- 145 in the last 30 days · 2.3K all time · 1 likes
- Published
- 2025-12-03 · updated 2025-12-03 (11mo ago)
- Languages
- en, fr, es, de, it, pt, nl, zh, ja, ko, ar
- Tags
- mistral3, mistral-common, fp8
Other MLX builds of mistralai/Ministral-3-14B-Instruct-2512
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| mistralai_Ministral-3-14B-Instruct-2512-MLX-MXFP4 | MXFP4 | ≈ 7.6 GB | 16 GB+ | 967 |
| Ministral-3-14B-Instruct-2512 (this one) | — | ≈ 27.0 GB | 48 GB+ | 145 |