한국어EN
Open-Weight LineageMistral AI

Mistral AI releases Mixtral 8x22B

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Released Mixtral 8x22B — a sparse MoE with 141B total / 39B active parameters, 64K context and native function calling, under Apache 2.0

Why it matters

Mistral's larger MoE follow-up to Mixtral 8x7B, again under Apache 2.0

Source — Primary sources first; secondary reports are labelled “Press”

Officialmistral.aihttps://mistral.ai/news/mixtral-8x22b

Added in Week 41, 2026 · See that week

On the map — ⑨ Open-Weight Lineage line

  1. Previous stopMistral Large
  2. This recordMixtral 8x22B
  3. Next stopEXAONE 3.0
See it on the map

In the model family tree — Mistral family · 13 versions

  1. Earlier versionMistral Large
  2. This recordMixtral 8x22B
  3. Later versionMistral Large 2
See the whole Mistral family

Same week

Hugging Face releases FineWebOfficialJapan publishes AI Guidelines for Business Ver1.0OfficialLlama 3 (8B/70B, about 15T tokens)Press

Nearby on the same axis

Llama 3 (8B/70B, about 15T tokens)PressNTT starts accepting applications for its in-house LLM tsuzumiOfficialxAI releases Grok-1 base model weights and architecture under Apache 2.0OfficialMistral AI releases CodestralOfficial