Unverified50% confidenceBenchmarkExact time
With MTP enabled, Qwen3.8 Flash Next maintains a generation speed of over 100 tokens per second across all tested context lengths, with the prefill phase exceeding 10,000 tokens per second throughout.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/2/2026
First Seen
Valid until: 12/1/2026
Sources
Related Entities
Related Claims
UnverifiedAfter enabling MTP, inference speed fluctuates significantly, sometimes exceeding 40 tokens/second and sometimes dropping to 25 tokens/second.74% similarUnverifiedIn the Flappy Bird HTML game generation test, the speed without MTP enabled was 31.15 tokens/second, and reached 37.3 tokens/second with MTP enabled, an improvement of approximately 20%.70% similarUnverifiedFlash模型的推理延迟通常在数百毫秒级别，而Pro/Ultra级别模型可能需要数秒甚至更长63% similarUnverifiedDuring the prefill phase, Ornith's speed approached 200 tokens per second, approximately 20 tokens faster than Qwen.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/843534API
curl https://kongchang.com/api/v1/knowledge/claims/843534MCP
get_claim(id=843534)