... . --> pavilion-weeyuga-v1 — qwen2.5/qwen2.5-coder/qwen3/qwen3.5 on pavilion — benchmarks.weeyuga.com
← All benchmarks
Headline Methodology Results Raw

Archive · 28 APR 2026 · Pavilion · HP laptop · GTX 1050 4 GB · 16 GB RAM · i7-9750H · qwen2.5/qwen2.5-coder/qwen3/qwen3.5 · chat

pavilion-weeyuga-v1 — qwen2.5/qwen2.5-coder/qwen3/qwen3.5 on pavilion

17 calls across 16 cell(s); 3 errors

Archive run

This run is published for transparency. The site-grade is archive-only — the run was meta-only, didn’t complete cleanly, lacked documented methodology, or had a methodology issue a newer run supersedes. Headline numbers in this row should not be cited as current findings without reading any caveat below and the underlying run.md in the public archive.

Methodology

See PAVILION_WEEYUGA_v1 for the full procedure. Reproducible at git SHA 99348927.

Results

Cell tok/s mean tok/s p50 tok/s p95 duration p50 calls
qwen3.5:4b2
qwen3.5:35b-a3b-uncensored-iq1m1
qwen3.5:35b-a3b-iq2s1
qwen3.5:9b-q6k1
qwen3.5:9b-q4km1
qwen3.5:2b1
qwen3.5:0.8b1
qwen3.5:9b1
qwen2.5-coder:14b1
qwen2.5-coder:3b1
qwen3:14b1
qwen3:8b1
qwen3:4b1
qwen2.5:3b1
qwen2.5-coder:1.5b1
qwen2.5-coder:0.5b1

tokens per second — mean · p50 · p95

No tokens-per-second data captured.

Raw data

Every run gets its JSONL, log, summary, and metadata published. Clone the archive; re-run it; tell us where we got it wrong.

Cite

Margetic, S. et al. (2026). benchmarks.weeyuga.com/benchmarks/ff1131ca.html
Public benchmarks of the Weeyuga cluster. Run id: ff1131ca-d021-4e06-8616-4b4cdb54e97e. SHA 99348927.

Related runs