DeepSeek V4 Flash 284B (13B active)
on Unknown GPU · llama.cpp · 253,000 ctx
Summary
User reports a 29x speedup on DeepSeek V4 Flash after profiling llama.cpp.
The gains come from fixing a CUDA attention kernel fallback, MoE tile padding, and using the MTP head for decode.
Prefill runs at 443 t/s at 97k context and 256 t/s at 253k context, with decode at 37 t/s. The model is 284B in 2bit, 87GB, and fits in 96GB VRAM.