17°

Reels · 9 of 11

21 s

Reel · 21 s

Does Qwen3.8-27B fit in 16 GB of VRAM? I measured it, and found out my own benchmark was lying

In 21 seconds: why the file weighs 17 GB and not 15, how the model splits between CPU and GPU depending on context, and the benchmark bug the model uncovered. Muted by default: turn it on in the controls.

Length
21 s
Published

ModelosGPUBenchmarks

This reel sums up Does Qwen3.8-27B fit in 16 GB of VRAM? I measured it, and found out my own benchmark was lying, where the method, the tables and what did not work are.

Read the articleOpen in the viewer