DeepSeek V4 Flash 284B (13B active)
on 4× AMD Radeon Pro V620 32GB · llama.cpp · 300,000 ctx
Sep 7, 2026
Summary
User reports DeepSeek-V4-Flash-0731 at 21.06 t/s continuous generation and 30.59 t/s sustained accepted generation on 4x AMD Radeon Pro V620 with 128 GB total.
Setup is the unsloth IQ3_XXS quant with speculative decoding using a DSpark Q8 drafter on CPU RAM and 2 draft tokens. Prompt ingestion is 276.23 t/s at 32K and 379.01 t/s at 4K.
The user calls the model at q3_xxs "fucking stupid" and lobotomized, and notes there is not enough VRAM for the drafter, which affects TG speeds.