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.
More from coding & agent
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16
- Builder's one rule for trusted desktop agents: read freely, but sending, deleting, buying always ask first — No_Fan5310 · 2026-10-16
- GPT-built unifi-simulator makes MikroTik switches appear inside UniFi Network — Pytlicek · 2026-10-16