Benchmark: Qwen3.8-27B leads small model agent capabilities

karminski3 · x · 2026-08-31

Benchmark results for small model agent capabilities. The Qwen3.8-27B-UD-Q4KXL version performs best on a single H100 with llama.cpp. Recommended config: reasoningeffort=low for agent tasks, medium/high for coding. Mac users should prefer MLX, as MTP is faster than llama.cpp on macOS.

Original post →

More from coding & agent

coding & agent channel →