⚙️ Optimization & Model Theory
Focus: Improving the model's raw intelligence and speed. The "Making it Better" stage. Technical mechanics of the LLM.
Agentic LLM Inference Tuning Reference for Qwen 3.6 and Gemma 4
This page is a practical reference for agentic LLM inference tuning (temperature, top_p, top_k, p...
Qwen 3.6 27B and 35B MTP vs Standard on 16GB GPU
I tested Speculative decoding (Multi-Token Prediction, MTP) performance in Qwen 3.6 27B and 35B o...