Reasoning · Pi Tune · MTP · GGUF Qwen3.6 27B tuned for reasoning heavy local coding agents. A 4 bit QLoRA SFT reasoning release for Pi style terminal loops: inspect the repo, plan the fix, run commands, edit files, validate, and recover when the first attempt fails. 🧠 Qwen3.6 27B base 🔎 Reasoning supervised ⚡ MTP speculative decoding 🛠️ Coding · DevOps · Agents 📦 llama.cpp GGUF 🖼️ Vision sidecar compatible 🪟 128k tested context 🧭 Better planning before action Trained on passed agent trajectories with reasoning preserved, so the model can decompose tasks before committing to commands and edits. 🧪 Verifier driven debugging Strongest in loops where the agent can run tests, inspect failures, patch code, and validate the whole task end to end. ⚡ MTP at every quant The MTP next token draft heads are kept at Q8 0 precision inside each quant, enabling speculative decoding even with low bit GGUF files. 🚀 Start with Q4 K M The default recommendation is Q4 K M: a practical quality / memory tradeoff for local coding agent experiments. Model overview Attribute Details Base model Qwen/Qwen3.6 27B Format GGUF Runtime target llama.cpp / OpenAI compatible local serving Tuning focus Pi styl…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy