<![CDATA[New benchmark evidence: completed provider comparisons]]>These four captures show why the dashboard keeps provider rows and analysis separate. The same machine can produce a different winner in a different run, and a composite recommendation is never allowed to erase the underlying values.

Interactive gallery: https://lizard-llm.qendryx.com/benchmarks.html

Five rows, five completed measurements

Completed five-row provider comparison

Ollama records 8.56 tok/s, stock llama.cpp Q4 7.85, and Lizard Native Q4 5.61 in this run. Load, warm-up and memory evidence stay visible beside throughput.

A second run changes the order

Expanded ten-row provider comparison

In this separate 10/10 run, llama.cpp Q4 reaches 6.23 tok/s, Lizard Native Q4 5.28, and Ollama 4.53. The result belongs to this model, machine and run—not a universal ranking.

Leaderboard plus metric-specific winners

Provider leaderboard and insight panel

Ollama leads the composite score, Lizard Native Q4 takes best native decode and parity among the compared rows, and llama.cpp Q4 leads wall time and end-to-end tokens per second.

Recommendations stay attached to source evidence

Wide benchmark leaderboard and evidence panel

Scores, badges, execution lanes and raw provider values remain on the same screen. The recommendation annotates the run; it does not replace it.

Question for you: On your hardware, which decision should come first: shortest wall time, steady decode speed, peak memory, or answer parity?

]]>https://community.lizard-llm.qendryx.com/topic/26/new-benchmark-evidence-completed-provider-comparisonsRSS for NodeMon, 24 Aug 2026 03:20:07 GMTWed, 22 Jul 2026 15:56:46 GMT60