Unverified50% confidenceFactExact time
Mistral Large 4 adopts a Mixture of Experts (MoE) architecture with a total parameter count of approximately 1 trillion, activating approximately 50 billion parameters per token
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe study covers 17 instruction-fine-tuned models spanning 8 architectural families, with parameter scales ranging from 1.5 billion to 72 billion.69% similarVerifiedMeta's Llama 3 has up to 405 billion parameters.69% similarVerifiedThe parameter counts of current mainstream large models have generally reached the trillion level.68% similarUnverifiedDeepSeek's flagship version has approximately 1.6 trillion total parameters and 49 billion activated parameters; the lightweight Flash version has 284 billion total parameters and 13 billion activated parameters, supports a context window of 1 million tokens, and is open-sourced under the MIT license.67% similarUnverifiedMistral Large 4 has a context window of 1 million tokens65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/982288API
curl https://kongchang.com/api/v1/knowledge/claims/982288MCP
get_claim(id=982288)