User tunes Qwen 3.8 27b on M5 Max, criticizes Opus instruction following
julianharris · x · 2026-08-16
A user is optimizing settings for Qwen 3.8 27b on an M5 Max (128GB), balancing factors like MTP, KV optimizations, resolution, and a 128k context window for coding. They also noted thermal throttling on the 14" chassis. Additionally, the user criticized the Opus model's instruction following capabilities, stating it remains mediocre and requires constant supervision compared to previous versions.
More from coding & agent
- BBOT Open Source Scanner Automates Bug Bounty Recon and ASM — tom_doerr · 2026-08-17
- CAKE Paper: Evolving Compiler Harness via AI for SOTA Kernels — lazowska · 2026-08-17
- GitHub Spec Kit: Define specs before letting AI agents build code — Shruti_0810 · 2026-08-17
- TradingAgents: Open-source multi-agent LLM trading framework — mdancho84 · 2026-08-17
- Making local models useful for coding: Hybrid cloud planning with local micro-patches — djpaul666 · 2026-08-17
- SpaceX Officially Closes Cursor Acquisition; Cursor Says It Now Has Access to 'Largest Fleet of GPUs in the World' — HaktanSuren · 2026-08-17