Posts tagged "LLM"

• Simple Tools, Smarter Agents

  Why mirroring a REST API into MCP tools suffocates AI agents — and how switching to dynamic, lazy-loaded tools cut context usage by 98%.

  Bogdan Szabo09 Apr 20266 mins read

• Running MiniMax M2.5 Locally with Claude Code

  A quick how-to guide for connecting Claude Code to your local MiniMax M2.5 inference server.

  Michael Mueller24 Feb 2026

• Running MiniMax M2.5 Locally on NVIDIA DGX Spark

  How I got a 230B parameter open model running on desktop hardware using NVIDIA DGX Spark, Unsloth quantization, and llama.cpp - matching cloud API performance without cloud dependencies.

  Michael Mueller19 Feb 2026

• Meet Reachy Mini: Building an AI-Powered Conference Badge Reader

  How I built a fun conference booth experience combining an open-source robot, vision AI, and Python. Plus: exploring local LLMs as the next step.

  Michael Mueller19 Jan 202620 mins read

• Llama and DeepSeek with LibreChat for Conversational AI

  Step-by-step guide: Deploy Llama and DeepSeek LLMs using SGLang on DataCrunch, and integrate with LibreChat for seamless conversations.

  Michael Mueller19 Feb 202520 mins read

• What are Large Language Models and Key Terminologies

  Learn about Large Language Models (LLMs), the Transformer architecture, tokenization, embeddings, and their impact on natural language processing.

  Michael Mueller03 Oct 202420 mins read