What are the hardware requirements for Mistral Large Instruct 2407 FP8?

Mistral Large Instruct 2407 FP8 requires approximately 123.6 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mistral Large Instruct 2407 FP8 and how large is it?

Mistral Large Instruct 2407 FP8 is developed by alpindale, a model with 122.6b 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 Large Instruct 2407 FP8?

Mistral Large Instruct 2407 FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mistral Large Instruct 2407 FP8 by alpindale — VRAM 123.6GB, 128K context

Name: Mistral Large Instruct 2407 FP8
Author: alpindale

Mistral Large Instruct 2407 FP8 is an open-source language model by alpindale. Features: 122.6b LLM, VRAM: 123.6GB, Context: 128K, License: other, Instruction-Based, LLM Explorer Score: 0.14.

Base model:finetune:mistralai/... Base model:mistralai/mistral-l... Chat Conversational De En Es Fr Instruct It Ja Mistral Pt Region:us Ru Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/alpindale/Mistral-Large-Instruct-2407-FP8

Mistral Large Instruct 2407 FP8 Parameters and Internals

Model Type

text-generation

Additional Notes

The weights have been converted to FP8 format, with FP8 weights, FP8 activations, and FP8 KV cache.

Supported Languages

en (supported), fr (supported), de (supported), es (supported), it (supported), pt (supported), ru (supported), zh (supported), ja (supported)

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text

LLM Name	Mistral Large Instruct 2407 FP8
Repository 🤗	https://huggingface.co/alpindale/Mistral-Large-Instruct-2407-FP8
Base Model(s)	Mistral Large Instruct 2407 mistralai/Mistral-Large-Instruct-2407
Model Size	122.6b
Required VRAM	123.6 GB
Updated	2026-07-17
Maintainer	alpindale
Model Type	mistral
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-26 4.8 GB: 2-of-26 4.9 GB: 3-of-26 4.8 GB: 4-of-26 4.9 GB: 5-of-26 4.8 GB: 6-of-26 4.9 GB: 7-of-26 4.8 GB: 8-of-26 4.9 GB: 9-of-26 4.8 GB: 10-of-26 4.9 GB: 11-of-26 4.8 GB: 12-of-26 4.9 GB: 13-of-26 4.8 GB: 14-of-26 4.9 GB: 15-of-26 4.8 GB: 16-of-26 4.9 GB: 17-of-26 4.8 GB: 18-of-26 4.9 GB: 19-of-26 4.8 GB: 20-of-26 4.9 GB: 21-of-26 4.8 GB: 22-of-26 4.9 GB: 23-of-26 4.8 GB: 24-of-26 4.9 GB: 25-of-26 2.2 GB: 26-of-26
Supported Languages	en fr de es it pt ru zh ja
Model Architecture	MistralForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.44.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the Mistral Large Instruct 2407 FP8 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 Large Instruct 2407 FP8

Best Alternatives	Context / RAM	Downloads	Likes
Mistral Large Instruct 2407	128K / 226.7 GB	4983	865
...CriminalComputing.LARGE.2026.3	128K / 217.2 GB	1981	63
Writer Large 2411 V2.1	128K / 222 GB	4	18
...arge Instruct 2407 XMADai INT4	128K / 31.7 GB	8	7
Mistral Large Instruct 2407	32K / 226.7 GB	13	2
...istral Large Instruct 2407 AWQ	128K / 64.5 GB	50	11

Note: green Score (e.g. "73.2") means that the model is better than alpindale/Mistral-Large-Instruct-2407-FP8.