# @mimi10v3 — 2026-10-13

♥2 ↻0 · https://x.com/mimi10v3/status/2109842227203576200

@albrorithm running a quantized qwen 3.8 27B on my 3090 w 24gb vram, and yeah having a local model on vllm does open up some possibilities... i have mostly just built out tools and enjoyed having it around but should try more experiments at some point

tags: author:mimi10v3, kind:tweet, on:qwen-3-8-27b, year:2026
cited on: _dossiers/qwen-3-8-27b.md, qwen-3-8-27b