~$11 per billion tokens: decentralized-trained model's inference optimizations revealed

bittingthembits · x · 2026-09-13

jondurbin quotes his team's decentralized training run, priced around $11/b tokens with impressive MFU. But he stresses the real point isn't the training itself — it's the inference optimizations the architecture enables:

Numbers come from an unoptimized vllm branch on their own arch, and he caveats the comparison isn't fully fair. Core claim: limitless tokens on cheap hardware, using a few nodes from liumio.

Original post →

More from Infra

Infra channel →