RTX 3090 Hits High Long-Context Throughput with 33B Model
GreenGames · hn · 2026-07-11
A Hacker News benchmark share reveals that running Laguna XS 2.1 33B on an RTX 3090 achieves a peak speed of 296 tok/s, while maintaining 152 tok/s at a 256K context length.
The focus here isn't on the model's release, but rather on a concrete local deployment / long-context inference performance metric, making it highly relevant for those interested in single-GPU inference, throughput, and context costs.
More from Infra
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11