Unverified50% confidenceEventExact time
Doug Ware tested Alibaba's open-source model Quen 3.8 Flash Next (a 125-billion-parameter MoE model that activates 6 billion parameters per token) within two weeks on a Strix Halo mini PC with 128GB of memory and an NVIDIA CUDA workstation.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/29/2026
First Seen
Valid until: 11/12/2026
Sources
Related Entities
Related Claims
VerifiedStrix Halo uses TSMC's 4nm process, integrates 16 Zen 5 CPU cores and 40 RDNA 3.5 compute unit GPU, and supports a unified memory pool of up to 128GB LPDDR5X.70% similarUnverifiedA Qwen Flash model released by Alibaba at the end of August also places 51 billion n-gram parameters in system memory for execution.68% similarUnverifiedThe Engram n-gram memory module of DeepSeek-V4.1-Flash occupies 196 billion parameters.68% similarUnverifiedStrix Halo是AMD于2024年底推出的旗舰移动平台，其最大技术突破在于统一内存架构（UMA），将CPU与GPU内存池合并为单一LPDDR5X内存，最高支持128GB，带宽可达256GB/s67% similarVerifiedV4.1 Flash activates 8 billion parameters when processing input and activates 16 billion parameters when generating output.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1112030API
curl https://kongchang.com/api/v1/knowledge/claims/1112030MCP
get_claim(id=1112030)