Strata runs a 125B model on a 12GB GPU at 96 tok/s, one-click local install

daluoseo · x · 2026-10-03

A look at Strata, an open-source inference engine (7.2k GitHub stars) that runs Qwen3.8-Flash-Next — a 125B-parameter model that normally needs a server — on consumer gaming PCs with just 12GB of VRAM (NVIDIA or AMD), reportedly hitting 96 tokens/s.

Highlights:

Caveat: the "Qwen3.8-Flash-Next" model name doesn't match official Qwen releases, so the project's claims warrant verification.

Related event: Strata Lets Consumer PCs Run 180B Models Locally(3 posts)→

Original post →

More from Infra

Infra channel →