Qwen3.8-27B announced to run locally on 17GB RAM/VRAM
Melvin Vivas · X post · 2026-08-03 · Open on X
Topics: Industry Trends & Job Market, LLM Fundamentals · Level: beginner
Summary
The creator shares the announcement that Qwen3.8-27B is coming and will run locally on setups with 17GB of RAM/VRAM. That makes it a candidate for running on consumer hardware.
Key points
- Qwen3.8-27B is announced as coming soon.
- The announcement says it will run locally with about 17GB of RAM/VRAM.
Resources mentioned
- Qwen3.8-27B · tool · huggingface.co · free
A 27B-parameter open-weight model from Alibaba's Qwen family that you can run locally or call through hosted APIs.
Also in: The Open Env Arena: Agents Design RL Environments, Ranked on a Leaderboard (Melvin Vivas on X · notes), Qwen3.8-27B on HF Inference Endpoints: Context Size Matters for Agent Builds (Melvin Vivas on X · notes), Deploying Qwen3.8 27B on Hugging Face Inference Endpoints (Melvin Vivas on X · notes), Using Hugging Face credits: Jobs, Inference Endpoints and Open Models (Melvin Vivas on X · notes) and 26 more
More in Industry Trends & Job Market
- Meta Muse Glimmer-30B: Open Weights Model That Beats Qwen3.6 37B on Agentic Tasks
- Liquid AI Documentation and the Future of Local AI
- Running MiniMax H3 Locally on a Single RTX 3090 (Demo)
- Qwen3.8-Max announced with open weights for Max and 27B
- Grok Can Now Analyze Videos
- DeepSeek-V4-Flash Official API Launches in Public Beta