DeepSeek V4 Flash 284B (13B active)
on NVIDIA RTX 3090 · text-generation-webui · 384,000 ctx
Summary
User reports DeepSeek-V4-Flash-0731 UD-IQ3_S running under the llama.cpp loader in text-generation-webui.
Setup uses --n-cpu-moe 39 to offload MoE experts to system RAM, with the loader estimating roughly 136 GB total and relying on 128 GB of DDR5 at 5600 MHz.