Benchmark search · Arao AI

Try these searches

2 matching benchmark runs

ModelQwen3.6-27BHardware: AllFramework: AllQuantization: AllEvidence level: AllSource: All

L0 Self-reported

NVIDIA RTX 3090 · 24GB · llama.cpp

GitHub

Today

46.57 tok/s

Decode

1,201.22 tok/s

Prefill

0.1 s

TTFT

21.53 GB

VRAM

Config (latest run):

Debian GNU/Linux 13 (trixie) CUDA 13.3 Q5_K_S llama.cpp v0.3.0-e0663be2713c

Sources: GitHub · 1 runs · 1 independent sources

L0 Self-reported

NVIDIA RTX 3090 Ti · 24GB · llama.cpp

GitHub

Today

50.84 tok/s

Decode

1,376.9 tok/s

Prefill

0.09 s

TTFT

22.47 GB

VRAM

Config (latest run):

Ubuntu 24.04.4 LTS CUDA 13.0 Q5_K_S llama.cpp v0.3.0-e0663be2713c

Sources: GitHub · 1 runs · 1 independent sources

2 results