Models chosen to fit real consumer GPUs.

Small, open-weight, quantised — because a marketplace on idle gaming hardware only works if the models actually fit in that hardware.

Launch candidates

DEMO — illustrative only, not real data

ModelLicenceSize (Q4)VRAM neededStatus
Qwen3-4BApache 2.0~2.5 GB~4 GBPlanned — not yet serving live traffic
Qwen3-8BApache 2.0~5.2 GB6–8 GBPlanned — not yet serving live traffic
Qwen3-14BApache 2.0~9.3 GB~12 GBPlanned — not yet serving live traffic
Llama-3.1-8BLlama 3 Community License — commercial use under 700M monthly active users~5 GB6–8 GBPlanned — not yet serving live traffic
Mistral-7BApache 2.0~4.5 GB6 GBPlanned — not yet serving live traffic

Sizes are approximate Q4_K_M quantised weights; VRAM figures include runtime overhead. Model identifiers in the API: qwen3-4b, qwen3-8b, qwen3-14b, llama-3.1-8b, mistral-7b. Licences were checked against the model publishers’ published terms at research time; final serving depends on a licence re-check before launch.

How models are chosen

Small (1B–4B) first for broad compatibility, then medium (7B–8B), then larger (12B–14B) for machines with 12 GB+ VRAM. A model is only listed as supported once it has actually run and been benchmarked on representative provider hardware — never on a spec sheet alone.

Chat playground

Talk to the demo backend. This POSTs to http://localhost:8787/v1/chat/completions with an OpenAI-compatible body. If the backend is not running, the error is shown honestly below — nothing is faked.

Replies from the demo backend will appear here.