LLM EXPLORER 58,133 MODELS INDEXED

Ministral 3 14B Instruct 2512 by mlx-community

By mlx-community · 60 downloads
HF Repo ↗ Copy URL

Ministral 3 14B Instruct 2512 is an open-source language model by mlx-community. Features: 14b LLM, VRAM: 27GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.

  Ar Base model:mistralai/ministral... Base model:quantized:mistralai...   Conversational   De   En   Es   Fp8   Fr   Instruct   It   Ja   Ko   Mistral-common   Mistral3   Mlx   Nl   Pt   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/Ministral-3-14B-Instruct-2512 

Ministral 3 14B Instruct 2512 Parameters and Internals

LLM NameMinistral 3 14B Instruct 2512
Repository 🤗https://huggingface.co/mlx-community/Ministral-3-14B-Instruct-2512 
Base Model(s)  Ministral 3 14B Instruct 2512   mistralai/Ministral-3-14B-Instruct-2512
Model Size14b
Required VRAM27 GB
Updated2026-08-10
Maintainermlx-community
Model Typemistral3
Instruction-BasedYes
Model Files  5.3 GB: 1-of-6   5.3 GB: 2-of-6   5.2 GB: 3-of-6   5.3 GB: 4-of-6   4.6 GB: 5-of-6   1.3 GB: 6-of-6
Supported Languagesen fr es de it pt nl zh ja ko ar
Model ArchitectureMistral3ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.0.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<pad>

Best Alternatives to Ministral 3 14B Instruct 2512

Best Alternatives
Context / RAM
Downloads
Likes
... 3 14B Instruct 2512 MLX MXFP40K / 7.2 GB5262
Amaretto 14B0K / 28 GB6980
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Ministral-3-14B-Instruct-2512.