Qwable 27B is a full Hugging Face checkpoint fine tuned from qwen/Qwen3.6 27B on a cleaned Fable 5 style reasoning and instruction dataset. The goal of this model is simple: take a strong Qwen 27B base and push it toward more deliberate, structured, trace like assistant behavior, especially for code, technical reasoning, and instruction following workflows. This is not a LoRA adapter. This repository contains the full fine tuned model checkpoint . Highlights Base: qwen/Qwen3.6 27B Checkpoint type: full HF model checkpoint Training style: instruction tuning with trace/reasoning style examples Dataset: cleaned Fable 5 reasoning/instruction dataset Primary focus: coding, structured answers, technical assistance, and local inference MTP: present in this checkpoint Local friendly goal: designed with downstream GGUF conversion in mind Model summary Field Value Base model qwen/Qwen3.6 27B Architecture Qwen3 5ForConditionalGeneration Model type qwen3 5 Checkpoint type Full HF checkpoint PEFT / LoRA No MTP layers present Training style Instruction + trace style fine tuning Primary use Code, reasoning, structured assistant responses What this model is good at Qwable 27B was tuned to be usefu…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy