UK · pounds · no account

Is it cheaper to run the model, or rent the API?

For people who use Ollama, LM Studio or llama.cpp, and for small firms deciding whether to buy a GPU or keep paying the API. The sums are in pounds, and every number has a source or is labelled an estimate.

The job

Chatbot for a small team Summarise 1,000 documents Coding assistant all day

8 people, 25 questions on each of 21 working days. 1,500 tokens in (the question plus a short history) and 400 tokens out. A worked example, not a log from a real team.

Tokens in, per job

Tokens out, per job

Jobs per month

Model and card Model GPU

What you would pay for the card, £

from £739.99 at Overclockers UK, checked 11 November 2026.

Electricity, pence per kWh

I already own this GPU

Ofgem price cap, average electricity unit rate for a Direct Debit customer in England, Scotland and Wales on a single-rate default tariff. No VAT on electricity in this period, per Ofgem. The daily standing charge is not included. Your region and payment method can differ. Ofgem, 1 October 2026 to 31 December 2026.

Speed and power

Tokens per second

Filled when a sourced run exists. Otherwise type the speed you see in Ollama, LM Studio or llama.cpp.

Watts

Starts at the card's maximum rated power. Lower it if you measured the draw.

Check the figures

DeepSeek: R1 0528's weights are larger than GeForce RTX 5070's 12 GB on the whole ladder — Q2_K alone is about 256.7 GB. As a MoE model it can run with its experts offloaded to system RAM, but far slower than a card that fits, and this site will not quote a speed for that setup. Choose a smaller model, or a card (or several) that holds the weights.