DeepSeek V4 Flash 284B (13B active)
on 8× NVIDIA RTX 5090 · llama.cpp · 5,632 ctx
Summary
User compares quants of DeepSeek V4 Flash 0731 on 8x RTX 5090, benchmarking with wikitext-2 at 5632 context and reporting PPL and top-1 accuracy.
The quant named AD-IQ2_M is 104 GB and reaches 83.6% top-1.
The user mentions an H100 for comparison.