DeepSeek reportedly runs smaller-model inference on NVIDIA gaming GPUs, argues Teortaxes
teortaxesTex · x · 2026-09-26
Teortaxes cites a claim that DeepSeek is using NVIDIA gaming GPUs to run inference on smaller models, calling it an obvious move that pairs well with Jevons-style small models or a custom Qwen 35B. The quoted post from tugot17 argues that as RSI nears, labs' demand for frontier chips has no upper cap and everyone else gets priced out — making heterogeneous compute unavoidable.
More from Infra
- Benchmark maker says no Ascend version — models would hill-climb it; TPU/Trainium/AMD better — xeophon · 2026-09-26
- FT: Oracle Must Pay Data Center Investors Even If Sites Never Get Power — SumitGup · 2026-09-26
- China Telecom's Xing4.0 trends on HF: 29B MoE trained entirely on Ascend 910C — AdinaYakup · 2026-09-26
- Data Center Resistance Is Growing in Africa: Scholar Digs Into the Backlash — ChinasaTOkolo · 2026-09-26
- Citi: monthly AI token usage has grown 31% MoM on average since early 2025 — Beth_Kindig · 2026-09-26
- Chanos and Gary Marcus question Nvidia: even the best chips won't sell if customers can't profit — GaryMarcus · 2026-09-26