Laguna XS 2.1 33B on a RTX 3090: 296 tok/s peak, 152 tok/s at 256K context
GreenGames
13 points
0 comments
July 11, 2026
Related Discussions
Found 5 related stories in 94.0ms across 9,716 title embeddings via pgvector HNSW
- Running Qwen3.8 at 255 tok/s on a single 5090 Ir0n · 12 pts · October 13, 2026 · 59% similar
- Laguna S 2.1 rexledesma · 275 pts · July 21, 2026 · 58% similar
- Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s snehesht · 696 pts · October 04, 2026 · 57% similar
- Qwen3.8 27B at 256K: 50 TPS on a 24 GB GPU pich · 37 pts · August 17, 2026 · 57% similar
- Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s carloslfu · 187 pts · September 01, 2026 · 52% similar