50GRAMx Think

How Think works.

Every step, and which machine does it. Your site is held on grams you own; the network’s edges carry it to visitors.

1You ask2A gram is chosen3The model runs4The step is signed5You get both
  1. 1
    You askIn the app, to Evo, or from your own program on a gram.
  2. 2
    A gram is chosenOne of your grams with a healthy engine for that model takes the turn.
  3. 3
    The model runsOn that gram’s CPU or GPU, with your data where it already is.
  4. 4
    The step is signedThe gram signs what it ran, with the model and the machine.
  5. 5
    You get bothThe answer comes back with its signed receipts.

Seen on a real gram

A signed measurement of this machine
$ epnd bench cpu
{
  "result": {
    "metric": "cpu.throughput",
    "value": 153.80340074778266,
    "unit": "hashes/s",
    "node_did": "did:epn:0024080112208414…bd024bfdd68672",
    "extra": { "cpu_model": "Intel(R) Core(TM) i5-5350U CPU @ 1.80GHz", "cores_physical": 2 }
  },
  "signature": "A+lGCMXcikiDAoscA+e3wN8xyuPsl8Mn+ndf982Po8jf0FLa…"
}
cpu: 154 hashes/s over 507ms
Real output. Run on the founder’s Mac gram, 16 Nov 2026. The gram’s id and signature shortened.