Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
Merge f-022-fitauto: a model just short of fitting gets a smaller context / reserve / prompt chunk automatically (Gyro-M on 8 GB Arc)
Niko12214e83ef04d5e0