Compare Benchmark Runs

Put individual benchmark runs side by side — specific model, tool and hardware. The best value in each row is highlighted. Share the URL to share this comparison.

Add runs to compare from the Benchmarks page — tick the runs you want and hit “Compare”.

cmtbmth7cmtg6g5tcmtg3fi3

No data found for the current selection.

unsloth/Qwen3.8-Flash-Next-GGUF on NVIDIA GeForce RTX 5090 vs AtomicChat/Qwen3.8-Flash-Next-GGUF on NVIDIA GeForce RTX 5090 vs unsloth/Qwen3.8-Flash-Next-GGUF on NVIDIA GeForce RTX 5090 — local LLM run comparison | llm-bench.io