lone · n=1 · agreement —
qwen2.5-7b-instruct ollama q4_k_m
median 274.6 tok/s · range 274.6–274.6 · CV 0%
| handle | tok/s | delta | os | trust |
|---|---|---|---|---|
| test | 274.6 | — | Linux | measured |
peer scores
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
lone · n=1 · agreement —
median 274.6 tok/s · range 274.6–274.6 · CV 0%
| handle | tok/s | delta | os | trust |
|---|---|---|---|---|
| test | 274.6 | — | Linux | measured |
lone · n=1 · agreement —
median 148.2 tok/s · range 148.2–148.2 · CV 0%
| handle | tok/s | delta | os | trust |
|---|---|---|---|---|
| test | 148.25 | — | Linux | measured |
lone · n=1 · agreement —
median 146.8 tok/s · range 146.8–146.8 · CV 0%
| handle | tok/s | delta | os | trust |
|---|---|---|---|---|
| test | 146.77 | — | Linux | measured |
lone · n=1 · agreement —
median 2.7 tok/s · range 2.7–2.7 · CV 0%
| handle | tok/s | delta | os | trust |
|---|---|---|---|---|
| test | 2.69 | — | Linux | measured |