Archive · vps-81 historical telemetry · models/qwen2_5_3b.html. Originally rendered 2026-04-16. Re-hosted from MyServers on 2026-05-06. Methodology and harness conventions may differ from what we use today; see /methodology.html for current standards. ← back to all benchmarks
Model Page

Qwen2.5 3B

TL;DR

This page indexes historical reports for Qwen2.5 3B. Labels such as “usable” describe the original harness checks, not independently verified correctness. Follow the linked reports for the test conditions.

qwen2.5:3b

Back to overview Family n/a Size 3b Max context n/a
Details
Recorded runtime labels

ollama

Report count

3 linked report pages

Findings captured

3 summary lines from local JSON artifacts

Findings
  • Latest small-eval run averaged 59.1s per question, 3/5 strict passes, and 5.57 tok/s throughput.
  • Latest 10Q suite on ollama averaged 62.9s for primary answers with 10/10 usable primary responses.
  • Latest 20Q suite on ollama averaged 33.3s for primary answers with 20/20 usable primary responses.
Benchmarks