lone · n=1 · agreement —
qwen3.8-27b ollama q4_k_m
median 131.4 tok/s · range 131.4–131.4 · CV 0%
| handle | tok/s | flags | os | trust |
|---|---|---|---|---|
| test | 131.45 | num_predict=256 temperature=0 |
— | signed |
peer scores · not a cert
Same class, different boxes
Agents query this as JSON. Similar spec = hardware class. Engine / quant / flags are separate recipes — we do not average them into one number.
RTX 5090 32GB · rtx-5090-32 · wiki