Alibaba's Qwen 3.8 Max Runs on All-Domestic Zhenwu M890 Chips, Reports Claim
bookwormengr · x · 2026-09-22
According to a post, Alibaba's new 2.4T-parameter Qwen 3.8 Max model reportedly runs inference entirely on domestic infrastructure — the first time China's homegrown AI stacks officially handle frontier-scale MoE workloads.
- Chips: proprietary Zhenwu M890 with 144GB memory and 800GB/s interconnect bandwidth
- Clusters: Panjiu AL128 supernodes with 128-chip scale-up
- Interconnect: proprietary ALink protocol (NVLink-like), with hints of adopting NPO to scale beyond 128 chips
- The post also frames the domestic stack landscape: DeepSeek+Huawei Ascend vs Moonshot+Alibaba (which holds a 30%+ stake in Moonshot), arguing Zhenwu shouldn't be overlooked despite Ascend's notoriety.
More from Infra
- Activist evicted in 2024 puts $5B Maryland AI data center on hold — ATTlKA · 2026-11-12
- Agent Substrate Calculator Estimates Session Resume Speed Under Load — pjausovec · 2026-11-12
- Dell expands AI Data Platform: agents have a data-context problem, not a model problem — DavidLinthicum · 2026-11-12
- SGLang Megakernel Pushes Muse Spark to 1,109 tok/s, 2.1x Over Baseline — hsu_byron · 2026-11-12
- Potion UI's local login system turns your PC into a multi-user AI server — cocktailpeanut · 2026-11-12
- AWS Finally Built Its Own AWS Emulator — super_linear · 2026-11-12