What are the hardware requirements for Ministral 3 14B Instruct 2512?

Ministral 3 14B Instruct 2512 requires approximately 15.8 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ministral 3 14B Instruct 2512 and how large is it?

Ministral 3 14B Instruct 2512 is developed by mistralai, a model with 14b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Ministral 3 14B Instruct 2512?

Ministral 3 14B Instruct 2512 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ministral 3 14B Instruct 2512 by mistralai — VRAM 15.8GB, 256K context

Name: Ministral 3 14B Instruct 2512
Author: mistralai

Ministral 3 14B Instruct 2512 is an open-source language model by mistralai. Features: 14b LLM, VRAM: 15.8GB, Context: 256K, License: MNPL-0.1, Instruction-Based, LLM Explorer Score: 0.31.

Arxiv:2601.08584 Ar Base model:mistralai/ministral... Base model:quantized:mistralai... De En Es Fp8 Fr Instruct It Ja Ko Mistral-common Mistral3 Nl Pt Region:us Safetensors Sharded Tensorflow Vllm Zh

Model Card on HF 🤗: https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512

Ministral 3 14B Instruct 2512 Parameters and Internals

LLM Name	Ministral 3 14B Instruct 2512
Repository 🤗	https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512
Base Model(s)	Ministral 3 14B Base 2512 mistralai/Ministral-3-14B-Base-2512
Model Size	14b
Required VRAM	15.8 GB
Updated	2026-06-29
Maintainer	mistralai
Instruction-Based	Yes
Model Files	15.7 GB 5.0 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 0.8 GB: 4-of-4
Supported Languages	en fr es de it pt nl zh ja ko ar
Model Architecture	MambaSSM
License	MNPL-0.1
Context Length	262144
Model Max Length	262144
Tokenizer Class	TokenizersBackend
Padding Token	<pad>
Vocabulary Size	131072

Rank the Ministral 3 14B Instruct 2512 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Ministral 3 14B Instruct 2512

Model	Likes	Downloads	VRAM
Amaretto 14B	3	440	28 GB

Best Alternatives to Ministral 3 14B Instruct 2512

Best Alternatives	Context / RAM	Downloads	Likes
...stral 3 14B Instruct 2512 BF16	256K / 28 GB	22294	29