Verified65% confidenceFactExact time
Mistral Large 4 uses a MoE architecture with 1 trillion total parameters and 49 billion active parameters, is natively multimodal, and has a context window of 512,000 tokens.
3
Sources
65%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
Unverified自托管 Mistral Large 4 按每参数 8 位计算，1.05 万亿参数需要约 1TB 内存，还不含 KV 缓存和运行时开销。74% similarUnverifiedML4 is a model with 1 trillion total parameters and 52 billion active parameters, continuing Mistral's路线 on large-scale sparse architectures.71% similarUnverifiedMistral Large 4 has a context window of 500,000 tokens and a speed of approximately 116 tokens/second.71% similarVerifiedWhen models with hundreds of billions of parameters process a 128K context window, KV Cache can occupy tens of gigabytes of VRAM.70% similarUnverifiedMistral Large 4 文档标注的上下文窗口为 100 万 token，但部分第三方提供商的预览 API 目前限制在 52.4 万 token。70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/989137API
curl https://kongchang.com/api/v1/knowledge/claims/989137MCP
get_claim(id=989137)