Research: In-Depth Tech Analysis

How to Run Heavy Open-Source LLMs for Free Without a GPU

Learn how to run open-source LLMs using Kaggle's free GPU tier, Ollama, and ngrok. Skip the hardware costs, avoid API fees, and access your models from your phone or desktop.

June 12, 2026 Ryan Wong

open-source-llms ollama kaggle ngrok ai-infrastructure self-hosted

Open Source LLM Evaluation Report - MiniMax vs Kimi vs DeepSeek vs Qwen

We ran 13 standardized tasks across four leading open source models and scored every response from 0 to 10. Here is exactly what we found.

June 5, 2026 Ryan Wong

llm evaluation minimax kimi deepseek qwen open-source benchmark

Best CPU Embedding Model for RAG Systems - Self-Hosted Infinity Server Setup

Discover how to deploy a self-hosted RAG system using Infinity server with BGE-Large embeddings that outperforms OpenAI's ada model while eliminating API costs. Complete technical implementation guide with Docker setup.

December 28, 2025 Ryan Wong

AI RAG embeddings BGE-Large Infinity MiniLM self-hosted open-source vector-search retrieval-augmented-generation

How good is DeepSeek OCR?

DeepSeek-OCR goes beyond basic text extraction by understanding entire page layouts. We tested it on complex 19-page reports to evaluate its structural accuracy.

February 4, 2026 Ryan Wong

DeepSeek-OCR AI OCR Document Analysis Markdown Machine Learning

Best Open Model for Real Prompts

Having tested top AI models on real-world tasks, GPT-OSS-120B leads in technical performance, Qwen3 excels at research, while GPT-5 and DeepSeek shine in coding and analysis. See the full benchmark results.

October 18, 2025 Ryan Wong

AI LLM benchmarks model-comparison GPT-OSS Qwen3 DeepSeek research