What are the hardware requirements for Ministral 3B Instruct?

Ministral 3B Instruct requires approximately 6.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Ministral 3B Instruct is developed by ministral, 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 3B Instruct?

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

Ministral 3B Instruct by ministral — VRAM 6.7GB, 128K context

Name: Ministral 3B Instruct
Author: ministral

Ministral 3B Instruct is an open-source language model by ministral. Features: 3b LLM, VRAM: 6.7GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.15.

Conversational Deploy:azure En Endpoints compatible Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ministral/Ministral-3b-instruct

Ministral 3B Instruct Parameters and Internals

Model Type

text-generation

Additional Notes

Ministral is a smaller version of the Mistral model with a parameter size of 3 billion, designed for text generation in English.

Supported Languages

en (primary)

Training Details

Model Architecture:

GPT-like

LLM Name	Ministral 3B Instruct
Repository 🤗	https://huggingface.co/ministral/Ministral-3b-instruct
Model Size	3b
Required VRAM	6.7 GB
Updated	2026-07-08
Maintainer	ministral
Model Type	mistral
Instruction-Based	Yes
Model Files	3.0 GB: 1-of-3 3.0 GB: 2-of-3 0.7 GB: 3-of-3
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Ministral 3B Instruct 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 3B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Mistral 3B Instruct V0.2	32K / 11.5 GB	4	4
...inerva 3B Llama3 Instruct V0.1	16K / 5.8 GB	1252	0
Minerva 3B Instruct V1.0	16K / 5.8 GB	19	7
Minerva 3B Instruct V1.0	16K / 5.8 GB	12	7
Toffee 3B Beta	8K / 7.7 GB	254	0
Phi 3 Phituguese 3B FP16	4K / 7.6 GB	7	0
Mistral 3B Instruct V0.2 Init	32K / 5.7 GB	589	3

Note: green Score (e.g. "73.2") means that the model is better than ministral/Ministral-3b-instruct.