Running a local MoE model on a $300 decade-old laptop: 10 tok/s with 4GB VRAM
texhnolyze_d · x · 2026-11-21
A user shares that his $300 old HP ZBook (laptop Xeon, P1000 with 4GB VRAM, 64GB DDR4 RAM) — bought as a disposable machine for paperwork — can locally run an uncensored MoE Qwen model at 10 tok/s with readable, occasionally memorable outputs. He asks what the real intellectual-capability ceiling is for 10-year-old hardware at 8–10 tok/s, and whether more quality jumps are coming. teortaxesTex notes even 5-year-old laptops now get pre-AGI goodies.
More from Infra
- Chart: TSMC revenue up 1807% since 2005, no 'cyclical' slowdown in sight — BenBajarin · 2026-11-21
- Inkling 2 Small pretrained on 8.4T tokens in 68 hours, natively in NVFP4 — viksit · 2026-11-21
- Analysts clash over Nvidia: huge demand vs. Chamath's claim its over-earning era may be over — BenBajarin · 2026-11-21
- Together AI SVP Simran Arora to headline AI Dev NYC 2026 on AI as its own performance engineer — DeepLearningAI · 2026-11-21
- OpenAI's token efficiency obsession hints launches now wait for serving costs, not research readiness — VraserX · 2026-11-21
- Inside China's SERES super factory: an industrial brain orchestrates 3,000 robots — HaydnBelfield · 2026-11-21