DeepSeek V4 Flash 284B (13B active)
on NVIDIA RTX Pro 6000 Blackwell · llama.cpp · 524,288 ctx
Sep 7, 2026
Use cases
coding
Summary
User reports DSpark speculative decoding with the drafter in RAM running faster than in VRAM.
Setup uses a q8_0 KV cache, which allows 768K context with minimal decode loss.
LiveCodeBench scores 28/30 (93.3%).