Arao AI

Benchmark search

Try these searches

Found 1 run configurations

Each row is a run configuration (model + hardware + framework + quantization); repeated runs of the same setup are merged — raw counts appear in each result’s source line.

Modelgemma-4-26B-A4B-it

gemma-4-26B-A4B-it · Q4_K_M

L1 Reproduced

Apple M2 Ultra · llama.cpp

GitHub

Yesterday

79.11 tok/s

Decode

1,550 tok/s

Prefill

— s

TTFT

— GB

VRAM

Config (latest run)
macOS 26.5.1 Q4_K_M llama.cpp b11050

Sources: GitHub · 1 runs · 1 independent sources

View details

1 results

Related models
Related hardware
Related frameworks
Related quantizations