한국어EN
Open-Weight LineageMistral AI

Mistral AI releases Mixtral 8x22B

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

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