llamaperf
Sep 29, 2026
Throughput
43.6 t/s gen · 262.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
IQ2_XXS + Q2_K (GGUF)
System RAM
755 GB
VRAM reported
96 GB

Summary

User reports DeepSeek V4 Flash at 43.6 tok/s generation on a short prompt and 262 tok/s prefill on a 20K-token prompt on an RTX PRO 6000 Blackwell Max-Q. Setup is DwarfStar 4 (ds4.c) with an IQ2_XXS + Q2_K quant, single session, no MTP or speculative decoding. Generation drops to 31.4 tok/s at 50K context; peak VRAM observed 93,142 MiB of 95,593 MiB (95%).