Archive · vps-81 historical telemetry · models/qwen2_5_coder_14b.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 Coder 14B

TL;DR

This page indexes historical reports for Qwen2.5 Coder 14B. Labels such as “usable” describe the original harness checks, not independently verified correctness. Follow the linked reports for the test conditions.

qwen2.5-coder:14b

Back to overview Family qwen2.5-coder Size 14B Max context 32768
Details
Recorded runtime labels

ollama-local-mac

Report count

4 linked report pages

Findings captured

2 summary lines from local JSON artifacts

Findings
  • Latest hello-check finished in 138.3s on ollama-local-mac.
  • Latest small-eval run averaged 1990.4s per question, 3/5 strict passes, and 0.07 tok/s throughput.
Benchmarks