llamaperf

DeepSeek V4.1 Flash 552B (16B active)

on NVIDIA CMP 170HX 64GB (unlocked) · Project Maya

Tone: positiveNVIDIA hardware
Nov 2, 2026
Throughput
55-65 t/s gen · 900-1100 tokens/s prompt processing (prefill)Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
Quant
IQ2_XXS GSQ-RCO-GGUF (GGUF)
VRAM reported
64 GB

Summary

User reports DeepSeek V4.1 Flash running at 55-65 t/s decode and 900-1100 t/s prefill on a single unlocked CMP 170HX 64GB at 150W. Setup is Project Maya with an IQ2_XXS GSQ-RCO-GGUF (2.0 bpw) quant. Both figures are given as ranges. The user plans to retry at 250-300W once a server shroud arrives.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

DeepSeek V4.1 Flash 552B · 16B active at 3-bit by hardware

Bars are medians on one scale, 0 to 73.4 tokens/s. Press ▶ to watch text arrive at a row's speed.

Models most run on the NVIDIA CMP 170HX 64GB (unlocked)

Bars are medians on one scale, 0 to 116.0 tokens/s. Press ▶ to watch text arrive at a row's speed.

Everything reported on the NVIDIA CMP 170HX 64GB (unlocked) →Every DeepSeek V4.1 Flash report →Estimate DeepSeek V4.1 Flash on this card →