What are the hardware requirements for Ministral 3 3B Reasoning 2512?

Ministral 3 3B Reasoning 2512 requires approximately 7.7 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 3B Reasoning 2512 and how large is it?

Ministral 3 3B Reasoning 2512 is developed by mistralai, a model with 3b 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 3B Reasoning 2512?

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

Ministral 3 3B Reasoning 2512 by mistralai — VRAM 7.7GB, 256K context

Name: Ministral 3 3B Reasoning 2512
Author: mistralai

Ministral 3 3B Reasoning 2512 is an open-source language model by mistralai. Features: 3b LLM, VRAM: 7.7GB, Context: 256K, License: MNPL-0.1, LLM Explorer Score: 0.3.

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

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

Ministral 3 3B Reasoning 2512 Parameters and Internals

LLM Name	Ministral 3 3B Reasoning 2512
Repository 🤗	https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512
Base Model(s)	Ministral 3 3B Base 2512 mistralai/Ministral-3-3B-Base-2512
Model Size	3b
Required VRAM	7.7 GB
Updated	2026-08-08
Maintainer	mistralai
Model Files	7.7 GB 5.0 GB: 1-of-2 2.7 GB: 2-of-2
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	LlamaTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072

Rank the Ministral 3 3B Reasoning 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

Best Alternatives to Ministral 3 3B Reasoning 2512

Best Alternatives	Context / RAM	Downloads	Likes
Shieldstral 1.0 3B	256K / 7.7 GB	5651	211
Ministral 3 3B Instruct 2512	256K / 4.7 GB	1185626	255
...istral 3 3B Instruct 2512 BF16	256K / 7.7 GB	185245	34
Ministral 3 3B Base 2512	256K / 7.7 GB	13090	72
Ministral 3 3B Instruct 2512	256K / 7.7 GB	2214	4
Voxtral Mini 3B 2507	32K / 9.4 GB	542811	668
...3.2 3B Instruct QLORA INT4 EO8	0K / GB	105	74
...3B Instruct SpinQuant INT4 EO8	0K / GB	41	40
Shieldstral 1.0 3B MLX 4bit	256K / 2.8 GB	372	1

Note: green Score (e.g. "73.2") means that the model is better than mistralai/Ministral-3-3B-Reasoning-2512.