Model Cards / Mistral AI

Mixtral 8x22B Model Card

model card810 words·4 min read·Mar 31, 2026·Source
Summary

Mixtral 8x22B Model Card

A 246-word brief of a 810-word document. Published by Mistral AI. Version dated Mar 31, 2026.
01

What this is

Mixtral-8x22B-Instruct-v0.1 is an instruct fine-tuned version of Mixtral-8x22B-v0.1, released by Mistral AI with a card dated 2026-03-31. It is a sparse mixture-of-experts large language model released under the Apache-2.0 license. The card is structured primarily as an integration guide rather than a traditional model card.

02

Capabilities

The model supports five languages: English, Spanish, Italian, German, and French. It includes native function-calling support with tool call IDs of exactly 9 alphanumeric characters, exposed through both the mistral-common and HuggingFace transformers APIs. No benchmark scores, parameter counts, or context window sizes are stated in this document.

03

Evaluation methodology

Not disclosed in this document.

04

Safety testing

Not disclosed in this document.

05

Mitigations

The card references a privacy policy governing personal data processing but does not describe any content classifiers, refusal training, or safety mitigations applied to the model. No ASL or FSF tier is invoked.

06

Deployment and access

The model is available on HuggingFace under the Apache-2.0 license with an extra-gated repository requiring acknowledgment of Mistral AI's privacy policy. It is compatible with vLLM, mistral-inference, and HuggingFace transformers (version 4.42.0 or higher required for function calling). No API-tier restrictions, usage limits, or access-control tiers beyond the gated download are described.

07

Limitations

The card notes a tokenizer discrepancy: the HuggingFace tokenizer may not produce results identical to the mistral-common reference implementation, and community PRs to correct it are solicited. No other limitations are disclosed in this document.

08

What's new

This is the v0.1 release of the instruct variant; no prior instruct version is referenced and no changelog entries appear in the document.

Generated by Claude sonnet from the cleaned source on Apr 23, 2026. Passages in double quotes are verbatim from the source; other text is neutral paraphrase. For citation, use the original: original document · source SHA d66746849181.