23:11
2026-08-17
jonidimo.github.io
large-language-models
Qwen3.8-27B on a single RTX 3090: crash fix, 131K context, 9 myths
A 14-hour benchmark on a single NVIDIA GeForce RTX 3090 found that the Qwen3.8-27B hybrid SSM+attention model achieves a 131K context window on 24 GB VRAM, scoring 20/21 on a frontier test set, but cr…