<![CDATA[Strata: Run decent models on small hardware]]>Well someone finally made a decent engine for (smaller) MoE's such as Qwen 3.8 Flash Next for hardware that mere mortals can also own.
Link here

The numbers provided in the repo's README file are impressive, I hope there's more work put into this.
Unfortunately it only works on NVIDIA GPUs, and also has barebones support for multi-GPU setups.

No AI used
]]>https://airigs.net/topic/13/strata-run-decent-models-on-small-hardwareRSS for NodeMon, 02 Nov 2026 07:03:58 GMTWed, 30 Sep 2026 16:17:25 GMT60