DeepSeek V4 Flash 284B (13B active)

User requantized only the 129 routed expert tensors of DeepSeek-V4-Flash-0731 to IQ3_XXS, with down projections at IQ3_S, leaving attention, shared experts and router at Q8_0, BF16 and F32. The result is 111.37 GiB in four shards. Against the MXFP4 source, KLD is a mean of 0.2386 versus 0.2936 for UD-IQ3_S, top-1 is 84.65% versus 82.78%, and delta PPL is +0.536 versus +0.685, but the requant is 2.12 GiB larger and has a worse max KLD of 12.53 versus 11.13. On 5 mixed GPUs (2x 3090, 5060 Ti, 2x 4060 Ti, 96 GiB VRAM) with expert spill to CPU, speed is 13.91/13.57/13.26 t/s at depths 0/4096/16384 versus 9.88/9.69/9.51 for the MXFP4 source, roughly 1.4x. antirez's flat Q2 is 80.76 GiB, about 98% resident, at 30.27 t/s. The user notes known DSV4 SWA/rollback stall issues in llama.cpp and used a patched build.