Unverified50% confidenceFactExact time
A single local call has 99 tokens of arguments and 135 tokens of rendered result, i.e. 234 tokens per decision in steady state; if this is the first decision in a session, the fixed 685 is also added.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe author reproduced it on a T4 with the same model and testing method: at 8 concurrency, a single request decodes at 122–124 tokens/s, and the whole server produces 701–708 tokens/s, likewise about a 5.7-fold difference.69% similarUnverifiedUnder conditions of 2944 input tokens and 1024 output tokens, normal mode reaches 29.9 tokens per second, which improves to 48.4 tokens/s after enabling MTP2.69% similarUnverified父子分块策略用小块（128~256 Token）做精准检索，命中后返回其所属大块（512~1024 Token）作为上下文66% similarUnverifiedIn a pydantic-ai test, after 10 parallel tool calls (21 new blocks), the next request read 6,827 tokens from cache; after 11 calls (23 blocks), the read count was 0 and 7,534 tokens were written again.64% similarUnverifiedIn speculative sampling, when the acceptance rate of candidate tokens is high, the effective number of output tokens per forward pass can reach 2–4, thereby improving the overall generation speed by 1.5x–3x.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016999API
curl https://kongchang.com/api/v1/knowledge/claims/1016999MCP
get_claim(id=1016999)