Unverified50% confidenceFactExact time
Muse Spark Open has 256 experts per layer, the router selects 8 per token, and the experts account for about 97% of the model's parameters.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMuse Spark 1.3 achieved an accuracy rate of 98.1% in ultra-long context tests of one million tokens.71% similarUnverifiedMuse Spark Open has a parameter scale of 816B, with 42B activated parameters.66% similarUnverifiedMuse Spark 1.3 scores 48 on the Artificial Analysis Intelligence Index, just 6 weeks after Muse Wonder's release, an improvement of 4 index points in six weeks.64% similarUnverifiedThe Qwen3.6 35B model contains 256 experts, with each token activating only 8 routed experts and 1 shared expert, resulting in approximately 3B activated parameters during actual inference.64% similarUnverifiedMuse-Glimmer-30B在测试中通过了88%的题目62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041155API
curl https://kongchang.com/api/v1/knowledge/claims/1041155MCP
get_claim(id=1041155)