DeepSeek V4 Flash 284B (13B active)
on AMD Strix Halo 128GB · llama.cpp · 131,072 ctx
Summary
User reports a speculative decoding sweep with DSpark drafters, from a 20.48 t/s baseline to a peak of 28.5 t/s at n_max=3, a 1.39x gain.
Q2_K_S and Q8_0 drafters land within 1-3% of each other.
The user estimates 22-28 t/s for realistic mixed use, with prefill at 200-220 t/s at 64k context.