Alibaba Unveils Qwen3.8-Flash Preview: MoE Model with Next-Gen Architecture
Alibaba_Qwen · x · 2026-08-26
Alibaba released Qwen3.8-Flash, a multimodal MoE model serving as an early preview of the Qwen4 architecture. With 125B total parameters but only 6B active per token, it offers unmatched cost-efficiency. The new architecture features GDN+QSA hybrid attention, N-gram Embedding, and the Muon optimizer, reducing training costs to 1/9th of Qwen3.7-Plus. It shows strong performance on benchmarks like DeepSWE, SWE-bench Pro, and MathVision. The production version will be available via QwenCloud API at $0.16/1M input tokens and $0.47/1M output tokens.
More from Infra
- MiniCPM-V 4.7 runs a 35B MoE multimodal model on phones with just 3GB memory — nevrekaraishwa2 · 2026-10-15
- Nvidia Is Now Worth More Than the Entire Indian Stock Market — theteknosaur · 2026-10-15
- NVIDIA joins EU's AI in Science Enablers, offering compute, training and cloud resources — nordicinst · 2026-10-15
- Open source's hardware trap: data centers crowd out consumer GPUs, local LLMs become a privilege — Dante_77A · 2026-10-15
- NVIDIA backs EU AI in Science push as 35 supercomputers to serve 3M researchers — NVIDIA Blog · 2026-10-15
- Jensen Huang: 2027 AI bottleneck is 35GW of power, revenue justifies the capex — BG2 Pod · 2026-10-15