SemiAnalysis: GPT-6.1 Sol Ultrafast runs on NVIDIA GPUs at low batch size, not Cerebras
BenBajarin · x · 2026-09-30
SemiAnalysis claims OpenAI's latest GPT-6.1 Sol Ultrafast is NOT running on Cerebras but instead on NVIDIA GPUs at a low batch size. The post questions what this says about Cerebras and whether it will serve the model in the future. Unverified third-party analysis, but directly relevant to who supplies compute behind OpenAI's fastest inference tier.
More from Infra
- ReScraper: a 0.6B model replaces heuristic data-cleaning stacks, boosting pretraining up to 4.7% — XiongChenyan · 2026-09-30
- How Anthropic made claude.ai 3x faster in two weeks with Claude, merging 3,000+ changes — trq212 · 2026-09-30
- Running open-source music model YuE2 on an AMD RX9070 under Linux: full setup guide — ATA-3D · 2026-09-30
- LLM-42 Paper at SOSP 2026 Brings Deterministic LLM Inference via Verified Speculation — tianyin_xu · 2026-09-30
- Indonesia's AI Debate: Owning a Data Center Doesn't Mean Owning the Decisions — AryHHAry · 2026-09-30
- Tesla secures $30B credit line to accelerate AI infrastructure, robotaxis and chip manufacturing — Polymarket · 2026-09-30