Qwen3.8 125B (6B active) Swift-1.5 Flash-Next
on NVIDIA RTX 5090 Laptop 24GB · PolyStrata · 131,072 ctx
Summary
User reports Qwen3.8 Swift-1.5 Flash-Next at 125.5 tok/s generation and 2,993.2 tok/s prefill on an RTX 5090 Laptop 24 GB.
Setup is PolyStrata with an IQ2_XS GGUF of about 63.5 GiB, configured for 131,072 tokens of context, with 128 GB of system RAM.
The model is far larger than the card's 24 GB, so weights ran partly from system memory.