Unverified50% confidenceReleaseExact time
This update includes an MTP hotfix for Qwen3.8-Flash-Next, which according to the official description improves inference speed by approximately 2x.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
UnverifiedThrough MTP (Multi-Token Prediction) technology, the inference speed of Qwen3.8-Flash-Next and GLM-5.3-Flash is improved by up to 2x.78% similarUnverifiedThe Qwen3 series natively supports MTP.65% similarUnverifiedThe benchmark results of Qwen3.8 Flash Next are official Qwen data and have yet to be independently verified by third parties.63% similarUnverifiedQwen3.8-Flash-Next natively supports MTP, indicating that this capability was built in during the model training phase.62% similarUnverifiedUnder a dual-Spark TP2 configuration, Qwen 3.8 Flash achieves an inference speed of 55–70 tokens/s and supports 4 fully concurrent agents running simultaneously.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/932841API
curl https://kongchang.com/api/v1/knowledge/claims/932841MCP
get_claim(id=932841)