Unverified50% confidenceFactExact time
Flint has 40B total parameters and uses a MoE architecture, activating only 2.5B parameters during inference.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe MoE architecture activates only a small fraction of the 2.4T parameters during inference (typically 10–20%).70% similarUnverifiedMoE模型中'35B'指总参数量，每个token只激活少量Expert（通常2-4个），实际计算量可能仅相当于6-7B的Dense模型66% similarUnverified千问三235B MoE总参数量2350亿，但每次推理实际激活的参数约22B63% similarUnverifiedIn the MoE architecture, the Mixtral 8x7B model has a total of 46.7B parameters, but only approximately 12.9B parameters (2 experts) are activated per token, making inference costs close to those of a 13B dense model while achieving performance comparable to the 70B level.62% similarUnverified千问3.6的35B MOE模型每次只激活其中3B的参数61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1083647API
curl https://kongchang.com/api/v1/knowledge/claims/1083647MCP
get_claim(id=1083647)