MyColo measured local AI inference

Share card

bundle 19 · measured result · 7B

274.4 tok/s

hardware
NVIDIA GeForce RTX 5090
model
qwen2.5-7b-instruct · 845dbda0ea48ed74…
engine / quant / ctx
ollama · Q4_K_M · ctx 4096
workload
wl-smoke-qwen25-7b-ollama
trust
measured · lone · test · 2026-09-21 00:27:09

Throughput comparison

274.4 tok/s · baseline 273.7 · +0.2% · n=9

7B · qwen2.5-7b-instruct · your prior signed/measured runs (same recipe)

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

hash
ade019c08600e14414c6773486837c1b86928dcaa39ab84342f70a910eb84f44

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