Expired50% confidenceBenchmarkExact time
After switching to Max, the average token count surged to 5,000 (more than 10×), average latency rose to 50 seconds, and the slowest response reached 600 seconds.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/25/2026
First Seen
Valid until: 10/9/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn this test, the prefill speed was fixed at approximately 500–600 tokens/s, and the time to first token increased linearly with input length.76% similarUnverifiedOn an 8GB GPU, the token generation speed is approximately 4.2 to 5 tokens/second, and decreases from around 6 tokens/second to approximately 4.2 as the context grows longer.74% similarUnverifiedAfter enabling MTP, inference speed fluctuates significantly, sometimes exceeding 40 tokens/second and sometimes dropping to 25 tokens/second.70% similarUnverifiedThe P95 runtime of the author's prompts rose from under 7 minutes to over 16 minutes and 20 seconds70% similarUnverifiedJev completes classification tasks in only 70 to 500 milliseconds, which is 40 to 200 times faster than traditional LLMs.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/948904API
curl https://kongchang.com/api/v1/knowledge/claims/948904MCP
get_claim(id=948904)