2x NVIDIA RTX 3090

Desktop

1

Run records

1

Models covered

1

Frameworks covered

L0 Self-reported × 1

Evidence mix

Typical measured performance

Published benchmark averages per model × framework × quantization on this hardware.

  1. llama.cpp · UD-Q8_K_XL Decode 43.65 · Prefill 1600.18 ·

Key specs

VRAM
48 GB

Run records

1 configurations

ModelFrameworkQuantizationDecodeSamples
Qwen3.8-27Bllama.cppUD-Q8_K_XL43.6 tok/s1