What are the hardware requirements for Ministral 3 3B Base 2512 4bit?

Ministral 3 3B Base 2512 4bit requires approximately 2.8 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 3B Base 2512 4bit and how large is it?

Ministral 3 3B Base 2512 4bit is developed by mlx-community, 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 Base 2512 4bit?

Ministral 3 3B Base 2512 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ministral 3 3B Base 2512 4bit by mlx-community — VRAM 2.8GB, 256K context

Name: Ministral 3 3B Base 2512 4bit
Author: mlx-community

Ministral 3 3B Base 2512 4bit is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 2.8GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.25.

4-bit 4bit Ar Base-model Base model:mistralai/ministral... Base model:quantized:mistralai... De Edge En Es Fr Image-text-to-text It Ja Ko Ministral Ministral-3 Mistral-common Mistral3 Mlx Multimodal Nl Pt Quantized Region:us Safetensors Vision Vision-language Zh

Model Card on HF 🤗: https://huggingface.co/mlx-community/Ministral-3-3B-Base-2512-4bit

Ministral 3 3B Base 2512 4bit Parameters and Internals

LLM Name	Ministral 3 3B Base 2512 4bit
Repository 🤗	https://huggingface.co/mlx-community/Ministral-3-3B-Base-2512-4bit
Base Model(s)	Ministral 3 3B Base 2512 mistralai/Ministral-3-3B-Base-2512
Model Size	3b
Required VRAM	2.8 GB
Updated	2026-10-07
Maintainer	mlx-community
Model Files	2.8 GB
Supported Languages	en fr es de it pt nl zh ja ko ar
Quantization Type	4bit
Model Architecture	MambaSSM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Tokenizer Class	LlamaTokenizerFast
Padding Token	<pad>
Vocabulary Size	131072

Rank the Ministral 3 3B Base 2512 4bit 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 Base 2512 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Shieldstral 1.0 3B MLX 4bit	256K / 2.8 GB	196	2
Shieldstral 1.0 3B	256K / 7.7 GB	5651	211
Ministral 3 3B Instruct 2512	256K / 4.7 GB	1185626	255
Ministral 3 3B Reasoning 2512	256K / 7.7 GB	140084	117
...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
Ministral 3 3B Reasoning 2512	256K / 7.7 GB	1038	3
... 3B Instruct 2512 Heretic BF16	256K / 7.7 GB	35	0
Voxtral Mini 3B 2507	32K / 9.4 GB	542811	668

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Ministral-3-3B-Base-2512-4bit.