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
- ChatGPT Plus users report OpenAI quietly loosened usage caps over a weekend — Existing-Slide7395 · 2026-10-05
- Unverified claim: GPT-6.1 Sol is 8x more token-efficient than Opus 5.5 — haider1 · 2026-10-05
- Nvidia-backed Reflection to release open-weight model rivaling top Chinese open models — TheZachMueller · 2026-10-05
- OpenAI's DevDay dots agent called underwhelming in hands-on comparisons vs Grok Bot — alexisgallagher · 2026-10-05
- Are free AI users entering the worst era yet as rate limits tighten? — alegom · 2026-10-05
- Sarcastic vs stochastic parrot images: evidence of conceptual understanding — Financial-Local-5543 · 2026-10-05