# @witcheer — 2026-08-14

♥122 ↻12 · https://x.com/witcheer/status/2088316316205907970

Qwen3.8-27B running on my RTX 5090, on llama.cpp!

first numbers, Q4_K_M via Unsloth's day-0 GGUF, llama-bench:

- decode: 78 tok/s empty, 76 at 8k context, 71 at 32k. minus 9.6% at 32k deep

- prompt: 3,900 tok/s (pp512)

- 17.5GB VRAM serving at 8k, so 14GB spare on a 32GB card

quality board runs tonight, full quant ladder after.

![photo](../../../media/HPswnijXQAEgArm.jpg)
tags: author:witcheer, has-image, kind:image, kind:tweet, on:qwen-3-8-27b, year:2026
cited on: _dossiers/qwen-3-8-27b.md, qwen-3-8-27b