Qwen3.8-27B Open Weights Coming, Runs Locally on 17GB RAM
danielhanchen · x · 2026-08-03
UnslothAI announced that Alibaba's Qwen3.8-27B model is coming soon. Optimized for accessibility, the model will run locally on setups with just 17GB of RAM/VRAM, significantly lowering the hardware barrier for deploying high-end LLMs locally.
Additionally, Alibaba previewed the open-weights release of its flagship 2.4T parameter model, Qwen3.8-Max, next week, which demonstrates exceptional capabilities in autonomous coding and long-horizon planning.
More from Infra
- AMD MI355X Beats NVIDIA B200 in Kimi K3 Deployment with 952 tok/s — adrianscottcom · 2026-08-03
- MiniMax H3 Gets Day 0 Support in SGLang, Runs Locally on Dual RTX 5090s — ying11231 · 2026-08-03
- AirLLM Breaks VRAM Barrier: Runs 70B LLMs on a Single 4GB GPU — techNmak · 2026-08-03
- MiniMax H3 Open Weights Hit fal with Out-of-the-Box Inference Optimizations — gorkem · 2026-08-03
- ComfyUI Adds Day 0 Support for MiniMax Video Model, Slashing VRAM by 66% for RTX 3060 — crystal_alpine · 2026-08-03
- AMD Enters Open-Source LLM Arena with Instella-MoE-16B — airesearch12 · 2026-08-03