Which is The Best Qwen3.8-27B?
Which is the best fine-tune of Qwen3.8 27B that reduces the amount of thinking and reasoning tokens but still keeps the best accuracy for your particular use case? Thanks to Dell for Sponsoring the Compute #NVIDIA #DellProPrecision #DellProMax ThinkingCap: https://bottlecapai.com/post/thinkingcap-qwen3-8-27b/ Swift 1.5: https://ukisai.com/swift-1-5-27b QwenPi: https://huggingface.co/bytkim/Qwen3.8-27B-pi 2nd Channel: https://www.youtube.com/channel/UCUF7WtR4JpVbQqcQGrLeADw Twitter: https://x.com/Sam_Witteveen 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: https://drp.li/dIMes 👨💻Github: https://github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 — Why Reasoning Models Think Too Long 00:55 — Why AI Models Are Reducing Reasoning Tokens 01:19 — Qwen3.8: ThinkingCap, Swift 1.5 & QwenPi 02:05 — Qwen3.8 Reasoning Effort Explained 04:01 — What These Fine-Tunes Are Trying to Solve 04:51 — ThinkingCap 09:17 — Swift 1.5 11:39 — QwenPi 15:07 — Demo 17:20 — Coding, Logic, Math & SVG Results
