MyColo measured local AI inference

Share card

bundle 8 · measured result · 27B

100.7 tok/s

hardware
NVIDIA GeForce RTX 5090
model
qwen3.8-27b · 22130167c4c20e20…
engine / quant / ctx
ollama · Q4_K_M · ctx 4096
workload
wl-v1-qwen38-27b-ollama
trust
measured · lone · test · 2026-09-20 22:37:40

Throughput comparison

100.7 tok/s · baseline 147.5 · -31.7% · n=10

27B · qwen3.8-27b · your prior signed/measured runs (same recipe)

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

hash
07f9586edc0bb82c8fa6ef884e3d8142df4212c7c4d276138614d01718a18a51

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