🐙 Blogs

🐙 GPU COMPARISON MATRIX FOR AI / LLM WORKLOADS

Detailed technical comparison between five graphics cards: RTX 3060 12GB, RTX 5060 Ti 16GB, 9060 ...

🐙 Qwen3.7 Max compare with others

This is writing about Qwen3.7 Max review and fix a random python code from github. input prompt:...

🐙 Dense model vs MoE model

Introduction Modern Large Language Models (LLMs) are generally built using two major architectura...

🐙 Tenstorrent TT-LoudBox™ (Wormhole)

This document synthesizes the comprehensive hardware, software, and technical specifications of ...

🐙 Multi-Token Prediction (MTP): The Price of Breakthrough, The Value of Certainty

In the competitive landscape of Large Language Models (LLMs), Multi-Token Prediction (MTP) has em...

🐙 Google Turboquant + llama.cpp

🐲 Helloworld Google public Turboquant, which is KV-Cache smaller and fast enought. It reduce 16 b...