UTC

Mixtral 8x22B Instruct

Mistral AI · open weights · served by 5 providers · tool calling, pdf input

mistral/mixtral-8x22b-instruct

Weights
Open
Released
2024-04-17
Knowledge cutoff
2024-01-31
Context window
66K
Hugging Face repository

mistralai/Mixtral-8x22B-Instruct-v0.1 at commit cc88a6cc19, last changed 2025-07-24

Licence
apache-2.0
Access
Open download
Library
vllm
Formats
.safetensors
  • No model signature file is published with the weights.
  • Built on mistralai/Mixtral-8x22B-v0.1.

What the Hub's scanners report

46 weight files, 43 with a scan result. No scanner reports an issue with them.

The model at this commit, its 46 weight files with their SHA-256 and its base models.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • AI/ML APImistralai/mixtral-8x22b-instruct
  • Kilo Gatewaymistralai/mixtral-8x22b-instruct
  • NanoGPTmistralai/mixtral-8x22b-instruct-v0.1
  • OpenRoutermistralai/mixtral-8x22b-instruct
  • Prime Inferencemistralai/mixtral-8x22b-instruct
Client SDKs on ShieldMap
Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.