What are the hardware requirements for Mistral V0.3 6B?

Mistral V0.3 6B requires approximately 11.9 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 V0.3 6B and how large is it?

Mistral V0.3 6B is developed by pszemraj, 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 V0.3 6B perform on standard benchmarks?

Mistral V0.3 6B has the following published scores: MMLU 51.83. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mistral V0.3 6B by pszemraj — VRAM 11.9GB, 32K context

Name: Mistral V0.3 6B
Author: pszemraj

Mistral V0.3 6B is an open-source language model by pszemraj. Features: 7b LLM, VRAM: 11.9GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.18, Arc: 45.1, HellaSwag: 71.7, MMLU: 51.8, GSM8K: 8.3.

Axolotl Base model:finetune:pszemraj/m... Base model:pszemraj/mistral-7b... Dataset:bee-spoke-data/knowled... En Endpoints compatible Generated from trainer Mistral Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/pszemraj/Mistral-v0.3-6B

Mistral V0.3 6B Parameters and Internals

Model Type

text generation

Additional Notes

This model is fine-tuned with Axolotl and built with pruning techniques to optimize for model size and performance on specific tasks.

Training Details

Data Sources:

BEE-spoke-data/knowledge-inoc-concat-v1

Data Volume:

smorgasbord-tb-quality

Context Length:

4096

Model Architecture:

MistralForCausalLM

LLM Name	Mistral V0.3 6B
Repository 🤗	https://huggingface.co/pszemraj/Mistral-v0.3-6B
Base Model(s)	pszemraj/Mistral-7B-v0.3-prune6 pszemraj/Mistral-7B-v0.3-prune6
Model Size	7b
Required VRAM	11.9 GB
Updated	2026-07-30
Maintainer	pszemraj
Model Type	mistral
Model Files	5.0 GB: 1-of-3 5.0 GB: 2-of-3 1.9 GB: 3-of-3 0.0 GB
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the Mistral V0.3 6B 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 Mistral V0.3 6B

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 pszemraj/Mistral-v0.3-6B.