What are the hardware requirements for BioMistral 7B?

BioMistral 7B requires approximately 14.5 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed BioMistral 7B and how large is it?

BioMistral 7B is developed by BioMistral, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does BioMistral 7B perform on standard benchmarks?

BioMistral 7B has the following published scores: MMLU 55.56. Compare against reference models on this page or on the LLM Explorer leaderboards.

BioMistral 7B by BioMistral — VRAM 14.5GB, 32K context

Name: BioMistral 7B
Rating: 3.78 (9 reviews)
Author: BioMistral

BioMistral 7B is an open-source language model by BioMistral. Features: 7b LLM, VRAM: 14.5GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.22, Arc: 54.3, HellaSwag: 79.1, MMLU: 55.6.

Arxiv:2402.10373 Biology Conversational De Deploy:azure En Endpoints compatible Es Fr It Medical Mistral Nl Pl Pt Pytorch Region:us Ro Tensorboard

Model Card on HF 🤗: https://huggingface.co/BioMistral/BioMistral-7B

BioMistral 7B Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

research

Applications:

medical question answering, biomedical research

Limitations:

Not recommended for professional use without further testing.

Considerations:

Consider thorough testing and validation in real-world applications.

Additional Notes

Advised as a research tool with emphasis on further alignment and testing for medical use.

Supported Languages

fr (French), en (English), de (German), nl (Dutch), es (Spanish), pt (Portuguese), pl (Polish), ro (Romanian), it (Italian)

Training Details

Data Sources:

PubMed Central Open Access

Context Length:

2048

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text

LLM Name	BioMistral 7B
Repository 🤗	https://huggingface.co/BioMistral/BioMistral-7B
Model Size	7b
Required VRAM	14.5 GB
Updated	2026-08-25
Maintainer	BioMistral
Model Type	mistral
Model Files	14.5 GB
Supported Languages	fr en de nl es pt pl ro it
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.35.0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the BioMistral 7B 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 BioMistral 7B

Model	Likes	Downloads	VRAM
BioMistral 7B GGUF	58	2466	2 GB
...Mistral 7B Lora Finetuned 4bit	0	29	4 GB

Best Alternatives to BioMistral 7B

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	8470	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	8018	17
Hebrew Mistral 7B 200K	256K / 30 GB	23	15
Astral 256K 7B	250K / 14.4 GB	9	0
Astral 256K 7B V2	250K / 14.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than BioMistral/BioMistral-7B.