Unverified50% confidenceBenchmarkExact time
With a 256K prefix already cached and 4 users, 95% of requests get their first token within 1.66 seconds.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/16/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedA 200K token context request requires approximately 25× the KV-Cache memory compared to an 8K token request.72% similarUnverifiedWhen the context approaches 512K tokens, the prefill-decode disaggregated architecture ensures that users still receive the first response token within 800 milliseconds after reading an entire specification.71% similarUnverifiedIn actual testing, the prefill read speed for a 32K context reached 3,860 tokens per second.71% similarUnverifiedDeveloper Primitive reported: 91.2 tokens/s with speculative decoding off, reaching 142.6 tokens/s after enabling 3 speculative tokens, approximately a 56% speedup under the same configuration.69% similarUnverifiedWhen 32 requests share the same 4k-token system prompt, Superfluid's prefix cache hit rate reaches 97%, on par with Ollama, while mlx_lm.server is 0%.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1044824API
curl https://kongchang.com/api/v1/knowledge/claims/1044824MCP
get_claim(id=1044824)