llama.cpp sets Qwen3.8-27B default effort to medium
xlayn · hn · 2026-08-19
A recent update in the llama.cpp repository changes the default effort level for the Qwen3.8-27B template from 'xhigh' to 'medium'. This adjustment likely aims to optimize the trade-off between inference speed and generation quality for local deployments.
More from Models
- Google Criticized: Gemini 3.7 Still Missing From Its Own Jules Agent a Week Later — brandon_galang · 2026-08-24
- Qwen 27B 3.8 low quantization tested: Q3 XXS works well locally — jeremyckahn · 2026-08-24
- Users notice significant quality shift in GPT-5.6 output — haider1 · 2026-08-24
- Ramp Stats: Anthropic Opus 4.8 and Sonnet 4.6 Lead Usage — vista8 · 2026-08-24
- Tencent Releases UI-Mate-27B, a Desktop GUI Agent Model — tencent · 2026-08-24
- ConvRot Quant joins llama-cpp: Q6 accuracy nears Q8 quality — giveen · 2026-08-24