Qwen 3.8 27b fine-tune cuts verbose output by up to 40% with little quality loss
julianharris · x · 2026-09-22
- Developer julianharris highlights Qwen-3.8-27b-Swift, a fine-tune of Qwen 3.8 27b that slashes the model's notoriously verbose output by up to 40% without meaningfully affecting quality.
- It ships as a configuration in the awesome-local-ai repo (boxabirds/awesome-local-ai), which offers one-command installers that run models locally behind an OpenAI-compatible API with a coding agent (opencode) already wired up — including Ubuntu 24GB (llama.cpp) and macOS 64GB (MLX) scripts for the Swift fine-tune.
- The repo also contains benchmarks, model combination configs, Qwen 3.8 experiment demos, and other variants like flash-next, plus the author's article on local AI and fine-tunes.
More from coding & agent
- The Modern AI Stack: 100+ Tools Powering What's Underneath ChatGPT — Aiden_Tech_Ai · 2026-09-22
- OpenAI, Anthropic, and Cognition to launch personal agent platforms within a month — cephaloform · 2026-09-22
- Open-source SemIf: a 4B model on a 3090 beats Jev in Sentdex's toy test — Sentdex · 2026-09-22
- A 4B model beats Jev in hybrid agent setup that runs 13x faster at 56% cost — Sentdex · 2026-09-22
- Jev ships 7-page guide; dynamic context rated 10/10 for coding agents — ramagetime · 2026-09-22
- Spring AI model router sample: auto-tier prompts across four OpenAI models — therealdanvega · 2026-09-22