What are the hardware requirements for Mistral 7B V0.3?

Mistral 7B V0.3 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 Mistral 7B V0.3 and how large is it?

Mistral 7B V0.3 is developed by mistralai, 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 Mistral 7B V0.3 perform on standard benchmarks?

Mistral 7B V0.3 has the following published scores: MMLU 63.46. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mistral 7B V0.3 by mistralai — VRAM 14.5GB, 32K context

Name: Mistral 7B V0.3
Author: mistralai

Mistral 7B V0.3 is an open-source language model by mistralai. Features: 7b LLM, VRAM: 14.5GB, Context: 32K, License: MNPL-0.1, LLM Explorer Score: 0.28, Arc: 60.5, HellaSwag: 83, MMLU: 63.5, GSM8K: 34.5.

Mistral Mistral-common Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/mistralai/Mistral-7B-v0.3

Mistral 7B V0.3 Parameters and Internals

Model Type

text generation

Use Cases

Limitations:

The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms.

Considerations:

We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.

Additional Notes

The Mistral-7B-v0.3 has extended vocabulary to 32768 tokens.

LLM Name	Mistral 7B V0.3
Repository 🤗	https://huggingface.co/mistralai/Mistral-7B-v0.3
Model Size	7b
Required VRAM	14.5 GB
Updated	2026-08-05
Maintainer	mistralai
Model Type	mistral
Model Files	14.5 GB 5.0 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Model Architecture	MambaSSM
License	MNPL-0.1
Context Length	32768
Model Max Length	32768
Transformers Version	4.42.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the Mistral 7B V0.3 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 Mistral 7B V0.3

Model	Likes	Downloads	VRAM
Mistral 7B V0.3 Bnb 4bit	22	381323	4 GB
Mistral 7B V0.3 AWQ	0	23	4 GB

Best Alternatives to Mistral 7B V0.3

Best Alternatives	Context / RAM	Downloads	Likes
Mistral 7B Instruct V0.3	32K / 14.5 GB	5676238	2725
Llama 2 7B Chat	0K / GB	50	623
Mosslight 7B	0K / 14.5 GB	116	1
Mistral 7B Instruct V0.3	0K / 14.5 GB	6	0
Mathstral 7B V0.1	0K / 29 GB	4802	243
Llama 2 7B	0K / GB	149	4521

Note: green Score (e.g. "73.2") means that the model is better than mistralai/Mistral-7B-v0.3.