MyColo measured local AI inference

Share card

bundle 30 · measured result · 14B

146.5 tok/s

hardware
NVIDIA GeForce RTX 5090
model
qwen2.5-14b · 7cdf5a0187d5c58c…
engine / quant / ctx
ollama · Q4_K_M · ctx 4096
workload
wl-mid-qwen25-14b-ollama
trust
measured · lone · test · 2026-09-21 00:27:29

Throughput comparison

146.5 tok/s · baseline 146.2 · +0.2% · n=10

14B · qwen2.5-14b · your prior signed/measured runs (same recipe)

Same handle, hardware class, size track, and recipe version. Current run excluded.

hash
e40ded82b0657428007c6cfb5de6ade8abe908db390bb7b6c4ad29776d6f4f00

Hardware class

{
  "cpu": "AMD",
  "driver": "580.126.18",
  "gpu_or_soc": "NVIDIA GeForce RTX 5090",
  "os_name": "Linux",
  "stack": "cuda",
  "vram_or_unified_mib": 32607
}

Sign-offs

hardware receipt · JSON · measure