One H200 Isn't Enough for DeepSeek 4.1 Flash: Two GPUs at $10.59/hr
daluoseo · x · 2026-11-02
A user reports that a single H200 can't run DeepSeek 4.1 Flash, so they spun up two H200 SXM GPUs in the AP-JP-1 region at a combined $10.59/hr, with a screenshot showing the deployment running. A useful data point on self-hosting costs for the model.
More from Infra
- Marvell-Lumentum deal signals what it takes to compete with Broadcom — BenBajarin · 2026-11-02
- Sam Altman: AI query energy cost fell 1,000x-100,000x in 3-4 years — rohanpaul_ai · 2026-11-02
- Marvell and Lumentum to merge, targeting $550B AI connectivity market — BenBajarin · 2026-11-02
- Samsung chairman visits Yokohama advanced packaging lab, pledging ¥40B investment over five years — pstAsiatech · 2026-11-02
- Sam Altman meets Samsung executives in Korea to deepen memory chip and AI infrastructure cooperation — pstAsiatech · 2026-11-02
- Simulating 200,000 months: can your home AI rig pay rent at 2026 GPU prices? — LeviTurk · 2026-11-02