Expired60% confidenceFactTime unknown
Qwen 3.6 achieved a prefill speed of 400 tokens/second and a generation speed of close to 40 tokens/second during testing.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn decode speed tests, speeds of approximately 45 tokens/second are achievable within 20,000 tokens, dropping sharply to approximately 20 tokens/second beyond 30,000 tokens.77% similarUnverifiedAfter enabling MTP, inference speed fluctuates significantly, sometimes exceeding 40 tokens/second and sometimes dropping to 25 tokens/second.72% similarUnverifiedDuring the prefill phase, Ornith's speed approached 200 tokens per second, approximately 20 tokens faster than Qwen.72% similarUnverifiedIt is generally considered that single-concurrency output above 100 tokens/second is sufficient to achieve a smooth typewriter effect, and at approximately 200 tokens/second, generating a 2,000-character long text takes only about 10 seconds.71% 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%.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13912API
curl https://kongchang.com/api/v1/knowledge/claims/13912MCP
get_claim(id=13912)