NVIDIA RTX 3090 Ti

GPU

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 · Q5_K_S Decode 50.84 · Prefill 1376.9 ·

Key specs

VRAM
24 GB

Run records

1 configurations

ModelFrameworkQuantizationDecodeSamples
Qwen3.6-27Bllama.cppQ5_K_S50.8 tok/s1