GPU price hike hits even the 1080ti, as local LLM token-speed numbers circulate
HankYeomans · x · 2026-09-19
The poster notes the GPU price hike is so broad that even the "ancient" GTX 1080ti is about to go up in price. Quoted numbers show code-generation speeds: Gemma4 E4B 200 tok/s, Gemma4 12B 135 tok/s, Bonsai 2 at 25 tok/s (70-100+ with a drafter via a custom Pascal kernel). Jokes about restoring 3dfx Voodoo cards capture local-inference users' anxiety.
More from Infra
- Luminal runs large-scale FLUX.2 diffusion on AMD MI300X to cut cost per image — ycombinator · 2026-09-19
- Google Cloud adds native transactional queues to Spanner for in-database async work — rseroter · 2026-09-19
- AI Infra Summit: Penguin Solutions and Astera Labs Bet Big on CXL Memory Expansion — BenBajarin · 2026-09-19
- Jev seen as local-model stand-in for low-latency apps; open-weight RLCD models expected — HankYeomans · 2026-09-19
- Hands-On: Running On-Device VLM Inference on Arduino Ventuno Q's Hexagon NPU — HowDevelop · 2026-09-19
- Bonsai 2 27B quantized beats Gemma 4 12B and Qwen 3.5 9B in 7GB 3D generation test — Fun-Meaning-6474 · 2026-09-19