Configuration 1: a workstation with one card, about $13,000
An RTX 5090 with 32 GB cost $9,000 on 30 September 2026, plus a platform with 128 GB of RAM and a power supply from 1,000 W, which we estimate at $3,600–$4,200. It runs models up to 32B parameters for 1–3 users, and 70B models slowly, with part of the layers offloaded. Power under load is, by our estimate, about 800 W: 576 kWh a month, about $54 at the Moscow household rate of about $0.10. It sits in the office and is noisy.
Configuration 2: two 96 GB cards, about $30,000
Two RTX PRO 6000 cards at $13,000 each, plus a server platform that we estimate at $3,600–$4,800. By our calculation, with an 8,192-token context, 192 GB of video memory is enough for a 70B model in 8-bit for 10–20 users with batched output. In 16-bit, the same model fits up to 3 users, and a 235B model in 4-bit up to 7. Power is up to 1,200 W for the cards plus 300 W for the platform: about 1,080 kWh a month, $100 at the about $0.10 rate. Hosting in a data center costs from $90 a month for a server up to 300 W, plus $24 for each extra 100 W: about $400 a month for 1.5 kW.
Configuration 3: four H100 cards, from $120,000
Four H100 SXM5 cards at $28,000 each, plus a chassis that links the cards: from $120,000 per server. 320 GB of video memory runs models up to 400B parameters in 4-bit, about 260 GB with cache and headroom, or 70–235B models for dozens of parallel dialogs. By our calculation with an 8,192-token context, that is about 80 for a 70B model in 4-bit and about 45 for a 235B model; 671B models no longer fit. Power is up to 2,800 W for the cards and about 1,000 W for the rest: 2,736 kWh a month, $250 of electricity at the about $0.10 rate, and about $1,000 for hosting 4 kW. An industry publication estimates that a server for 1,000 concurrent users costs about $660,000, and to keep the token price reasonable, GPU load must stay at 80–90% or higher.
What else goes into the bill
Backup disks and a second power supply, a UPS, monitoring system licenses, a spare card, and the administrator’s time. A rule from practice: a server without a person to run it costs more than a server with one, because downtime costs more than a salary.