Qwen3.8-27B launches with 1M context on a single GPU, vLLM ready
Alibaba_Qwen · x · 2026-08-14
Alibaba's Qwen team releases Qwen3.8-27B, a 27B-parameter dense hybrid-attention model with linear attention on 48 of 64 layers, 262K native context extendable to 1M, multimodal support, and built-in MTP draft head. It runs on a single Blackwell GPU (24.6 GiB in NVFP4) and is available on vLLM 0.17.0 from day one.
Related event: Alibaba Open-Sources Native Multimodal Qwen3.8-27B Model(48 posts)→
More from Infra
- TokenSpeed MLA 2 hits NVIDIA Vera Rubin: up to 3.44x faster decode vs B200 — zhyncs42 · 2026-10-16
- US vs Chinese hyperscalers: Americans fund and schmooze, Chinese demand your BoM and cap you at 7% margin — jwt0625 · 2026-10-16
- How LiteLLM routes one OpenAI-shaped API across every model provider — Mahmoud_Zalt · 2026-10-16
- OpenAI-Broadcom custom AI chip Jalapeño named a TIME Best Invention of 2026 — itsclivetime · 2026-10-16
- Developer live-runs continual pretraining of a Luganda LLM on Colab, 41% done with loss dropping fast — weskambale · 2026-10-16
- Jensen Huang: Nvidia charges ~$thousands per GPU yearly for software, a major revenue line — rohanpaul_ai · 2026-10-16