Verified65% confidenceBenchmarkExact time
In 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+.
3
Sources
65%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn decode speed tests, speeds of approximately 45 tokens/second are achievable within 20,000 tokens, dropping sharply to approximately 20 tokens/second beyond 30,000 tokens.79% similarUnverifiedIn 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.77% similarUnverifiedLocal model inference speed is approximately 1–10 tokens/second, while cloud-based APIs can reach 50–150 tokens/second.77% similarUnverifiedAplomb 1 对短问题的模型端计算时间约 15 毫秒，端到端延迟约 200 毫秒71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/897649API
curl https://kongchang.com/api/v1/knowledge/claims/897649MCP
get_claim(id=897649)