Latest Posts

By Ryan A. on Mar 25, 2025

DeepSeek V3-0324 is an updated checkpoint with better coding performance and the same setup as previous versions. Here’s how to run it with the latest weights.

By Wei Ming T. on Mar 24, 2025

Performance comparison of TensorFlow, PyTorch, and JAX using a CNN model and synthetic dataset. Benchmarked on NVIDIA L4 GPU with consistent data and architecture to evaluate training time, memory usage, and model compilation behavior.

By Ryan A. on Mar 13, 2025

Learn the recommended GPU specifications for running Google DeepMind's latest Gemma 3 models efficiently, including VRAM requirements for text and image-to-text tasks.

By Ryan A. on Mar 12, 2025

Learn how to generate videos using Wan2.1, an advanced open-source video generation model. This guide walks you through installation, setup, and running text-to-video generation on consumer and high-end GPUs.

By Ryan A. on Mar 6, 2025

QwQ-32B is a 32-billion-parameter reasoning model optimized with reinforcement learning, rivaling larger models like DeepSeek-R1. This guide covers installation and running methods, including Hugging Face and an easier alternative using Ollama.

By Wei Ming T. on Mar 5, 2025

Comparing NVIDIA GPUs with Apple's macOS Metal GPUs for machine learning workloads. Performance tests include a deep learning rig, MacBook M3 Pro, MacBook Air M1, and Google Colab's free tier.

By Wei Ming T. on Mar 5, 2025

Learn how to run PyTorch on a Mac's GPU using Apple’s Metal backend for accelerated deep learning. This guide covers installation, device selection, and running computations on MPS.

By Jacob M. on Feb 25, 2025

Learn how to integrate and use the Claude 3.7 API, Anthropic’s latest hybrid reasoning AI model. This guide covers authentication, making API requests with cURL, Python, and JavaScript, and key features like extended reasoning and Claude Code.

By Wei Ming T. on Feb 23, 2025

As PyTorch continues to gain traction, is TensorFlow still worth learning in 2025? A deep dive into their strengths, industry adoption, and what matters for building a machine learning career.

By Sam G. on Feb 11, 2025

Essential strategies to efficiently scale RAG (Retrieval-Augmented Generation) for millions of documents, including vector database selection, indexing methods, reranking approaches, and optimized data ingestion pipelines.