My process to get 6-11X speedup running Qwen3.6 on my RTX 4090, full repo.
AI4Science
17 points
8 comments
November 13, 2026
Related Discussions
Found 5 related stories in 139.9ms across 12,728 title embeddings via pgvector HNSW
- Running Qwen3.8-Flash-Next NVFP4 at 184 tok/s on a single RTX 6000 Pro matteohorvath · 14 pts · October 26, 2026 · 70% similar
- Run QWEN3.8 27B on 16gb Nvidia GPUs Pragmata · 16 pts · September 17, 2026 · 67% similar
- Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s snehesht · 696 pts · October 04, 2026 · 67% similar
- Running Qwen3.8 at 255 tok/s on a single 5090 Ir0n · 12 pts · October 13, 2026 · 64% similar
- Qwen3.8 27B at 256K: 50 TPS on a 24 GB GPU pich · 37 pts · August 17, 2026 · 60% similar
Discussion Highlights (2 comments)
shutty
Nice but it would be also great to include strata and llamacpp to the benchmark. Otherwise it’s 11x speedup over the baseline no one uses
kennywinker
That's cool, but what are you doing that you want to run qwen3.6-35b-a3b, over qwen3.8-flash.next, which runs great on a 4090