Achieved steady 15 tokens/second output and 100-120 promp processing per second with 12GB GPU (RTX 5070 SFF) with Qwen3.8-Flash-Next-GSQ-RCO-GGUF at 3 bpw (IQ3_XXS which maches BF16 on AIME25). Around 76GB full gguf - while only 47GB needs to be sharded (loaded into VRAM+RAM) rest is done in SSD. Ou
