Which Qwen3.8-27B fine-tune is best? Comparing ThinkingCap, Swift 1.5 and QwenPi
Sam Witteveen · youtube · 2026-10-05
Sam Witteveen compares three Qwen3.8-27B fine-tunes — ThinkingCap, Swift 1.5, and QwenPi — that cut reasoning tokens while preserving accuracy. The video walks through each approach, a live demo, and benchmark results across coding, logic, math, and SVG tasks to help pick the right one per use case.
More from Models
- QuixiInfer: from-scratch Rust engine runs DeepSeek with 256k context on a single RTX 5090 at ~30 tok/s — QuixiAI · 2026-11-20
- Matthew Green questions why a compromised inference provider served an abliterated model — matthew_d_green · 2026-11-20
- GPT 6.2 Sol remains #1 for computer/browser use, says Matthew Berman — MatthewBerman · 2026-11-20
- Microsoft's MAI models have been front-page on Hacker News since Ignite debut — marlene_zw · 2026-11-20
- Gemini 4 Carbon tops graduate-level physics benchmark but loses on agentic tasks — ArtificialAnlys · 2026-11-20
- Neon and Hydrogen own every Pareto frontier in Gemini 4 lineup, from $0.29 to $6.44 per task — ArtificialAnlys · 2026-11-20