Expired50% confidenceBenchmarkExact time
In actual testing, the local model's single response took 0.6–0.8 seconds, output 20–37 tokens, at a speed of about 100–110 tok/s; the first rejection took 6.4 seconds due to cold start.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/28/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn this test, the model's output speed in short-context scenarios is approximately 20 tokens/second, dropping to approximately 13 tokens/second for contexts of 200K+.77% similarUnverifiedOn the same H100, a scale-to-zero cold wake-up took about 75 of 77.3 billed seconds before the server was capable of responding.74% similarUnverifiedAt approximately 115K context, the model requires about 21 minutes of waiting before it begins generating, decoding drops to approximately 14 tok/s, but all four integrity checks pass.72% similarUnverifiedGear backlash is typically only a fraction of a degree, and control latency is typically on the order of 5–20 milliseconds.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1025545API
curl https://kongchang.com/api/v1/knowledge/claims/1025545MCP
get_claim(id=1025545)