InGoogle Developer ExpertsbyCyrus Wong·1d agoLeveling the Playing Field: Building a 100% Offline Kubernetes Docs RAG Exam Assistant with WebAIHow to enable fair, zero-cost, air-gapped AI assistance in technical classrooms and assessments — running entirely in the browser
Kumuda·Oct 25The Pixel Hero Who Nags Me to Drink Water — My first week running AI on my own laptopBe honest. When did you last drink water while working?A response icon2A response icon2
Hossein Mortazavi·Oct 25Beyond Python: Benchmarking Modern SLMs (Gemma 4, Qwen 3 & Phi-4) on CPU with Pure Rust & CandleWhen I first shared my experiment on running Microsoft’s Phi-3 on a standard consumer CPU using pure Rust and Hugging Face’s Candle…
InGoPenAIbyKushal Pokhrel·Oct 21How I Built TOPAZ(Topological Agent for Zero-Bloat Code Reasoning): Competing in Google’s Gemma 4…A few weeks ago, Google launched the Gemma 4 Developer Agent Paper Track on Kaggle. One core challenge in the mind stood out immediately:
InRustaceansbyxbill·Oct 16Renting Out One T4 to Three Customers: Gemma 4, vLLM Multi-LoRA and a Rust GatewayThis is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle
xbill·Oct 15Inference Engineering with Gemma4This article provides a step by step tour of inference engineering across every platform I have served Gemma 4 on: Hugging Face as the…
InGoogle Cloud - Communitybyxbill·Oct 10Gemma 4 E2B in Pure JAX on a Colab TPU: Google's 4-Bit Export Against an Exact RepackThis article provides a step by step guide to a Colab notebook that serves Gemma 4 E2B on a single TPU v5e chip with a pure-JAX engine and…
Luca Massaron·Oct 5Gemma 4 12B Under the Microscope: BF16 vs.Can 4-bit NormalFloat quantization preserve the coding and analytical precision of Google’s flagship mid-sized multimodal model on local…
InTowards AWSbyxbill·Sep 30Gemma 4 on Amazon SageMaker: 4-Bit Embeddings Decode up to 1.39x Faster on One L4This article repacks Gemma 4’s quantization-aware trained (QAT) weights into several 4-bit and 8-bit formats and measures each one on the…
Borivoje Kovac·Sep 27Zeitgeist: Access Gets PoliticalJune shows that access to AI is no longer determined by the model alone: it depends on nationality, workplace systems, compute, price, and…
