Archive · vps-81 historical telemetry · models/qwen3_5_4b.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

Qwen3.5 4B

TL;DR

This page indexes historical reports for Qwen3.5 4B. Labels such as “usable” describe the original harness checks, not independently verified correctness. Follow the linked reports for the test conditions.

qwen3.5:4b

Back to overview Family qwen3.5 Size 4b Max context 32768
Details
Recorded runtime labels

ollama-local-mac

Report count

4 linked report pages

Findings captured

4 summary lines from local JSON artifacts

Findings
  • Latest hello-check finished in 14.4s on ollama-local-mac.
  • Latest small-eval run averaged 30.7s per question, 3/5 strict passes, and 6.57 tok/s throughput.
  • Latest 10Q suite on ollama-local-mac averaged 136.9s for primary answers with 10/10 usable primary responses.
  • Latest 20Q suite on ollama-local-mac averaged 35.3s for primary answers with 20/20 usable primary responses.
Benchmarks