Unverified50% confidenceBenchmarkExact time
In a test scenario where eight agents each process 7.5k-token documents and a chat request is issued in the second second, Superfluid answers in 0.36 seconds while llama-server outputs no first token for more than 10 seconds, a first-token latency gap of about 30 times.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedDuring an 8,000-token run, Ollama reported a duration of 125 seconds, while the client actually waited 725 seconds, with the difference being gateway queuing time that is invisible to the server-side numbers.74% similarUnverifiedIn the long-context archiving experiment, 8 requests each input approximately 261,000+ tokens and each completed approximately 1,022 outputs; the total throughput of the joint decoding window was 214.85 tokens per second, approximately 26.86 per request, but the window was only approximately 2.28 seconds and prefilling was serial or interleaved.74% similarUnverifiedThe MiMo V2.6 Pro cluster runs a hello test at approximately 15 tokens/second, dropping to approximately 12 tokens/second for complex tasks.72% similarUnverifiedIt is generally considered that single-concurrency output above 100 tokens/second is sufficient to achieve a smooth typewriter effect, and at approximately 200 tokens/second, generating a 2,000-character long text takes only about 10 seconds.72% similarUnverified对于500 Token的回答，流式输出可以让用户在首Token延迟（约500ms）后就开始看到内容，而非等待完整生成（约10秒）71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013608API
curl https://kongchang.com/api/v1/knowledge/claims/1013608MCP
get_claim(id=1013608)