Strata Runs A 125B Model On Gaming Pcs
Strata is an app that runs a quantized version of the 125-billion-parameter Qwen3.8-Flash-Next on consumer gaming PCs. The repository lists requirements of an NVIDIA or AMD GPU with 12GB or more of VRAM, 32GB or more of RAM, 80GB or more of storage, and Windows 10/11 or Linux. Reported runs hit 94 tokens/second on an RTX 5070 with 64GB RAM, but the 2-bit quantized build produced looping output in one prompt.