MyColo measured local AI inference

Share card

bundle 32 · measured result · 14B

146.3 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 00:27:33

Throughput comparison

146.3 tok/s · baseline 146.2 · +0.1% · 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
3c5559e78c5e5d10073806bf92cad38eb9cd8882e789e10b815845c42244f05b

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