Does a GPU pay for itself selling tokens? Pick a GPU and an open-weight model. A roofline model built from each model's real architecture estimates tokens per second at a speed users will accept. Those tokens are priced at what providers charge today, then set against power, hardware price and lifetime. The matrix at the bottom shows which GPU × model pairs make money and which never will.
Every GPU × model pair under your current workload, costs and price basis, each with its own best deployment. Colour is NPV relative to what the hardware costs — blue makes money, red loses it, grey is break-even. Click a cell to load that pair above.
The model gets the numbers on this page — the selected deal and the best and worst pairs in the matrix — and writes a short investment-committee note. It quotes the engine's numbers; it doesn't calculate them.
Each model's geometry comes from its config.json on Hugging Face: layers, KV heads, head size, experts, sliding windows, latent (MLA) or compressed attention, and the recurrent state of linear-attention and Mamba layers. Serving is modelled as one continuous-batching decode step with chunked prefill mixed in, as vLLM, SGLang and TensorRT-LLM do.
Calibration: with an MLPerf-style 300-in / 300-out load and no speed floor, Llama 70B gives about 3,000 output tok/s per H100 (MLPerf ≈ 3,000), 3,500 per MI300X (≈ 3,300) and 14,000 per B200 at FP4 (≈ 12,000). Treat results as ±25%. Speculative decoding and prefix caching, which real providers use, would raise throughput; heavy-tailed request lengths would lower it.
Not included: taxes, financing, staff, bandwidth, sales and payment fees, and the risk that newer models make yours unsellable before the hardware wears out.