DeepSeek V4 Flash 284B (13B active)
on NVIDIA RTX 4090 · llama.cpp · 65,536 ctx
Sep 7, 2026
Use cases
agenticcoding
Summary
User reports generation at 12.0-13.1 t/s and prompt processing at 212-224 t/s for 8k-32k tokens.
Setup uses --n-cpu-moe 39 to offload experts to CPU, and requires 128 GB RAM.
Agentic tasks take 15-26 minutes. No quality benchmarks were run.