Kimi K3 was partly trained on Blackwell GPUs, per The Information
teortaxesTex · x · 2026-07-28
A quote tweet questions how useful Blackwell GPUs really are for training V4, arguing they are cheap on hardware less than four years old and that 1e25 is not a huge amount of compute. The cited claim says Kimi K3 was partly trained on Blackwell GPUs alongside Qwen3.8 and DeepSeek, according to The Information.
Related event: Moonshot Reportedly Used Nvidia Blackwell for Kimi K3(2 posts)→
More from Infra
- Allen AI's OlmoEarth Maps N. America Wildfire Risk with 155x Speedup — allen_ai · 2026-07-29
- Databricks says AI agents are forcing a rethink of transactional and analytical databases — matei_zaharia · 2026-07-29
- China’s semiconductor push adds immersion DUV and near-Micron DRAM capacity — Distinct-Question-16 · 2026-07-29
- AI Flash Memory Crisis Worsens, Leaks Point to Return of 4GB GPUs — gnukeith · 2026-07-29
- Low-VRAM LoRA training now fits DeepSeek-V4-Flash into 90 GiB VRAM — woct0rdho · 2026-07-29
- YC startup hwintelligence launches Wave, a waveform debugger with a verification agent — ycombinator · 2026-07-29