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
- Altman says OpenAI aims to replace Nvidia in the medium to long term — zephyr_z9 · 2026-11-11
- Chinese University Bought Nvidia H200 Chips Despite US Blacklist — pstAsiatech · 2026-11-11
- Baidu's ERNIE Evolve tops public bests on NanoGPT Speedrun, brings RSI to real inference optimization — xiaohu · 2026-11-11
- Baidu says RSI auto-optimized ERNIE inference, 6.24x decode speedup on Kunxin P800 — xiaohu · 2026-11-11
- Nvidia's supply commitments jump from $119B to $279B in one quarter, locking up 2027-28 memory — tengyanAI · 2026-11-11
- Train 27B models on a 24GB GPU: ternary optimizer cuts memory to 1 byte/weight — oguzeldereli · 2026-11-11