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.
Not enough yet
The API comes to £1.04 a month for this job. There is no speed for running it locally, so the electricity and the break-even are left blank.
Memory. Google: Gemma 4 31B against GeForce RTX 4070 Ti SUPER's 16 GB, estimated from the Hub's published weight size across the common quants: BF16 62.5 GB no · Q8_0 33.2 GB no · Q6_K 25.8 GB no · Q5_K_M 22.3 GB no · Q4_K_M 19 GB no · IQ4_XS 16.6 GB no · Q3_K_M 15.2 GB yes · Q2_K 11.7 GB yes. The largest quant that fits is Q3_K_M at about 15.2 GB; lower quants trade quality for memory. Rule of thumb, not a measured file size.
- API this month
- £1.04
- Electricity this month
- Blank
- GPU purchase
- Not on file
- Break-even
- Needs a speed
- API cost is input tokens and output tokens, priced per million, times jobs per month. No caching, batch discount, or free tier.
- Pound figures use the stored exchange rate. They are not a quote from the company that trained the model.
- No tokens-per-second figure, so the electricity line is blank. Type one in if you have measured it.
- API price: £0.149 in and £0.298 out per million tokens, from $0.200 and $0.400 at 0.74501 dollars to the pound on 2026-11-10. OpenRouter feed 2026-11-11.
- GeForce RTX 4070 Ti SUPER: 16 GB GDDR6X. Total graphics power: 285 W. Specs read 2026-11-11.
- No sourced speed for this pair, and none was typed in.
- Upper estimate, based on the official total graphics power of 285 W.
OpenRouter prices · Exchange rate · GPU spec · Ofgem unit rate