Unverified50% confidenceFactExact time
Mixtral 8x7B is a mixture-of-experts architecture model released by Mistral in late 2023.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCosmopedia v2 是由 Mixtral-8x7B 等模型批量生成的合成数据集68% similarUnverifiedMixtral 8x7B, released by Mistral AI, is the first mainstream open-weight MoE model, with 46.7B total parameters and 12.9B active parameters.67% similarUnverifiedMixtral 8x7B was the first open-source MoE model to attract widespread industry attention, using 8 7B experts (46.7B total parameters, 12.9B activated) to achieve performance close to Llama 2 70B.62% similarUnverifiedGoogle 的 Switch Transformer（2021）和 Mistral 的 Mixtral 8x7B（2023）都采用了稀疏 MoE 架构，即每次前向传播只激活少数几个专家61% similarUnverifiedMixar is a fork based on Blender 5.0 that integrates AI capabilities into the core.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/967367API
curl https://kongchang.com/api/v1/knowledge/claims/967367MCP
get_claim(id=967367)