What are the hardware requirements for Mistral Supervised?

Mistral Supervised requires approximately 0.3 GB of VRAM and supports a context window of 0.5K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mistral Supervised and how large is it?

Mistral Supervised is developed by eperezj, a model with 84.5m 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 Mistral Supervised?

Mistral Supervised is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mistral Supervised by eperezj — VRAM 0.3GB, 0.5K context

Name: Mistral Supervised
Author: eperezj

Mistral Supervised is an open-source language model by eperezj. Features: 84.5m LLM, VRAM: 0.3GB, Context: 0.5K, LLM Explorer Score: 0.19.

Base model:eperezj/mistral-pre... Base model:finetune:eperezj/mi... Endpoints compatible Generated from trainer Mistral Region:us Safetensors Sft Trl

Model Card on HF 🤗: https://huggingface.co/eperezj/mistral-supervised

Mistral Supervised Parameters and Internals

LLM Name	Mistral Supervised
Repository 🤗	https://huggingface.co/eperezj/mistral-supervised
Model Name	mistral-supervised
Base Model(s)	Mistral Pretraining eperezj/mistral-pretraining
Model Size	84.5m
Required VRAM	0.3 GB
Updated	2026-08-07
Maintainer	eperezj
Model Type	mistral
Model Files	0.3 GB 0.0 GB
Model Architecture	MistralForCausalLM
Context Length	512
Model Max Length	512
Transformers Version	4.53.2
Tokenizer Class	LlamaTokenizerFast
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	float32

Rank the Mistral Supervised 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 Supervised

Best Alternatives	Context / RAM	Downloads
Mistral Pretrained Test	128K / 0.3 GB	7
Mistral Pretraining	0.5K / 0.3 GB	11
Mistral Pretraining	0.5K / 0.3 GB	13
Lab 2	0.5K / 0.3 GB	6
Mistral Pre Trained Model	0.5K / 0.3 GB	13
Mistral Pretraining	0.5K / 0.3 GB	5
Mistral Pretraining	0.5K / 0.3 GB	7
Mistral Pretraining	0.5K / 0.3 GB	10
Mistral Pretraining	0.5K / 0.3 GB	5
Mistral Pretraining	0.5K / 0.3 GB	5

Note: green Score (e.g. "73.2") means that the model is better than eperezj/mistral-supervised.