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.

ModelDeepSeek-V4-Flash-Vision-Exp

DeepSeek-V4-Flash-Vision-Exp · UD-Q8_K_XL

L0 Self-reported

2x NVIDIA RTX 5090 · 64GB · llama.cpp

GitHub

2026-09-27

32.08 tok/s

Decode

671.45 tok/s

Prefill

0.12 s

TTFT

60.59 GB

VRAM

Config (latest run)
Ubuntu 24.04.4 LTS CUDA 13.3 UD-Q8_K_XL llama.cpp moecachev1.6-rc0

Sources: GitHub · 1 runs · 1 independent sources

View details

1 results

Related models
Related hardware
Related frameworks
Related quantizations