Unverified50% confidenceBenchmarkExact time
After FP8 quantization, first-token latency rises noticeably with concurrency: 277ms at 32 concurrent requests, jumping to 1,300ms at 64; beyond 32 concurrent requests, throughput stops growing and latency deteriorates sharply.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
Unverified中继转发相比P2P直连往往会引入额外的30-80ms延迟67% similarVerifiedIn testing, the p99 latency per 160-millisecond tick was 147.4–147.5 milliseconds, with zero missed deadlines across three rounds totaling 84,000 session ticks measured.66% similarUnverifiedMaximem Synap claims a P75 recall latency of under 15 milliseconds64% similarUnverifiedWhen loading the Claude Code compatibility rule set, Armor's median latency increases by 279 ms and P90 by 334 ms.62% similarUnverifiedAfter honoring retry-after and layering full jitter on top, the last call completed at 11.8 seconds, 313 requests were sent, and p95 was 9.1 seconds, with every metric better than the two backoff formulas.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1071381API
curl https://kongchang.com/api/v1/knowledge/claims/1071381MCP
get_claim(id=1071381)