Every open model a machine of this kind has run on the network, at its fastest build, fastest first. Speed is tokens a second, measured and signed by the machine itself.
| Model | Fastest build here | tok/s | Context | $ / M tokens |
|---|---|---|---|---|
| Llama 3.2 1B | Q4_K_M (4-bit) by bartowski | 4.7 | 16K | $6.56 |
| Gemma 4 E2B | Q3_K_M (3-bit) by unsloth | 2.8 | 8K | $11.59 |
| Phi 4 Mini | Q3_K_L (3-bit) by maziyarpanahi | 2.2 | 128K | $13.85 |
| Phi 4 Mini-Reasoning | Q4_K_M (4-bit) by unsloth | 1.9 | — | $17.44 |