Matthew Berman
AI YouTube Creator & Host
Host of one of YouTube's largest applied AI and open-source machine learning channels with over 550,000 subscribers. Specializes in empirical foundation model benchmarking, local offline model deployment (Ollama, LM Studio), multi-agent frameworks, and autonomous workflow architecture.
Areas of focus
Professional niches
Watch Matthew Berman in Action
Proof of Work
Autonomous Agent Architectures and Workflow Templates
Maintains open-source implementation guides demonstrating multi-agent routing, tool calling, and structured output parsing with CrewAI, AutoGen, and LangChain.
Multi-agent coordination requires strict token budget controls to prevent runaways on recursive self-refinement.
Context: CrewAI multi-agent swarms, Python tool calling, SQLite persistence.
View missionRunning Frontier Open Weights and Local LLMs Fully Offline
Published hands-on architectural walkthrough testing quantization trade-offs, GPU VRAM caching, and local Ollama server orchestration across Llama-3, DeepSeek, and Mistral models.
Local inference throughput is bounded by available unified memory bandwidth on consumer workstations.
Context: Local quantized GGUF weights, Ollama, vLLM, LM Studio, consumer GPU hardware.
View mission