Expired50% confidenceBenchmarkExact time
Using the 33K-length Qwen3.8-Flash technical report as a long-text input example, the prefill phase speed is approximately 180 tok/s and the decoding phase is approximately 18 tok/s.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/16/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedAfter INT4 quantization, the Qwen3-0.6B model file is only about 400 MB, retains approximately 95% of baseline capability, and an ordinary laptop CPU can achieve a generation speed of 10–30 tokens per second.70% similarUnverifiedReplacing the text encoder from int8_convrot (1.67 s) with qwen3vl_32b_minimax_h3_nvfp4_awq (0.7 s) saves nearly one second per generation.69% similarUnverifiedQ4_K_M量化文件大小17.77GB，pp2048速度96.8 tok/s，tg128速度11.4 tok/s69% similarUnverifiedOn the Qwen 3.8 Flash Next model, decoding performance doubled to 52 tok/s.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924382API
curl https://kongchang.com/api/v1/knowledge/claims/924382MCP
get_claim(id=924382)