<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>MY AI Blog &amp; Guides (gomyai.uk)</title><description>Articles on client-side AI, WebGPU acceleration, privacy-first web architecture, and Transformers.js.</description><link>https://gomyai.uk/</link><language>en-us</language><item><title>Why Client-Side AI is the Ultimate Future of Web Privacy</title><link>https://gomyai.uk/blog/best-local-ai/</link><guid isPermaLink="true">https://gomyai.uk/blog/best-local-ai/</guid><description>Discover how running WebLLM and Transformers.js natively inside your browser delivers zero latency, complete data confidentiality, and offline capability.</description><pubDate>Tue, 28 Jul 2026 00:00:00 GMT</pubDate></item><item><title>BGRagNet &amp; MODNet: Browser-Based Vision AI for Automated Image Background Removal</title><link>https://gomyai.uk/blog/bgragnet-modnet-vision-ai/</link><guid isPermaLink="true">https://gomyai.uk/blog/bgragnet-modnet-vision-ai/</guid><description>In-depth guide to BGRagNet Small and MODNet vision segmentation models running in-browser via Transformers.js for automatic background removal and transparent PNG export.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Chrome Built-in AI &amp; Gemini Nano: The Zero-Download Native Browser AI Revolution</title><link>https://gomyai.uk/blog/chrome-native-ai-gemini-nano/</link><guid isPermaLink="true">https://gomyai.uk/blog/chrome-native-ai-gemini-nano/</guid><description>Discover Google Chrome&apos;s built-in AI APIs (Prompt, Summarizer, Translator APIs) powered by Gemini Nano, zero download overhead, performance benefits, and limitations.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate></item><item><title>WebGPU vs Cloud APIs: Client-Side AI Latency &amp; Performance Benchmarks</title><link>https://gomyai.uk/blog/client-side-ai-performance-benchmarks/</link><guid isPermaLink="true">https://gomyai.uk/blog/client-side-ai-performance-benchmarks/</guid><description>Empirical latency comparisons between browser-accelerated WebGPU execution and cloud-hosted LLM endpoints.</description><pubDate>Thu, 30 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Achieving 100% GDPR, HIPAA, &amp; SOC2 Compliance with In-Browser AI</title><link>https://gomyai.uk/blog/gdpr-hipaa-compliance-browser-ai/</link><guid isPermaLink="true">https://gomyai.uk/blog/gdpr-hipaa-compliance-browser-ai/</guid><description>How zero-server data architectures eliminate data liability risks for enterprise teams and sensitive document workflows.</description><pubDate>Thu, 30 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Demystifying Gemini Nano: Google’s Edge AI Engine Powering Android AICore</title><link>https://gomyai.uk/blog/gemini-nano-android-aicore/</link><guid isPermaLink="true">https://gomyai.uk/blog/gemini-nano-android-aicore/</guid><description>An in-depth look at Gemini Nano, Google&apos;s highly efficient LLM designed for on-device mobile AI. Explore its system architecture, real-world use cases, and Kotlin integration patterns.</description><pubDate>Sun, 02 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Gemma 2 2B IT: Google DeepMind&apos;s Advanced Model for Browser WebGPU Inference</title><link>https://gomyai.uk/blog/gemma-2-2b-it/</link><guid isPermaLink="true">https://gomyai.uk/blog/gemma-2-2b-it/</guid><description>In-depth technical analysis of Google DeepMind&apos;s Gemma 2 2B Instruct model, WebGPU runtime capabilities, VRAM footprint, limitations, and practical applications.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The Ultimate Gemma Models Comparison Guide: 2B, 9B, 27B, CodeGemma, PaliGemma &amp; DataGemma</title><link>https://gomyai.uk/blog/gemma-models-comparison-guide/</link><guid isPermaLink="true">https://gomyai.uk/blog/gemma-models-comparison-guide/</guid><description>Comprehensive technical breakdown of Google DeepMind&apos;s official Gemma open model family based on Google AI documentation. Explores Gemma 2 architecture, DataGemma RAG grounding, Gemma Scope interpretability, QLoRA fine-tuning, and WebGPU deployment.</description><pubDate>Sat, 01 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Kimi K2.5: Deep Dive into Moonshot AI&apos;s Multimodal Mixture-of-Experts &amp; Agent Swarm</title><link>https://gomyai.uk/blog/kimi-k2-5-deep-dive/</link><guid isPermaLink="true">https://gomyai.uk/blog/kimi-k2-5-deep-dive/</guid><description>An in-depth technical guide to Kimi K2.5, detailing its 1T Mixture-of-Experts (MoE) architecture, 256K context window, native vision-language processing, and parallel Agent Swarm orchestration.</description><pubDate>Tue, 11 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Llama 3.2 1B Instruct: Meta&apos;s Compact Powerhouse Running 100% Client-Side via WebGPU</title><link>https://gomyai.uk/blog/llama-3-2-1b-instruct/</link><guid isPermaLink="true">https://gomyai.uk/blog/llama-3-2-1b-instruct/</guid><description>Explore Meta&apos;s Llama 3.2 1B Instruct model architecture, browser deployment strategies, WebGPU performance metrics, limitations, and ideal use cases.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Building Privacy-First Web Apps with Zero Server Dependencies</title><link>https://gomyai.uk/blog/privacy-first-tools/</link><guid isPermaLink="true">https://gomyai.uk/blog/privacy-first-tools/</guid><description>How static web architecture combined with browser-based ML protects sensitive corporate data and personal workflows.</description><pubDate>Wed, 29 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Qwen2 0.5B Instruct: Ultra-Fast Client-Side LLM for Browser WebGPU Inference</title><link>https://gomyai.uk/blog/qwen2-0-5b-instruct/</link><guid isPermaLink="true">https://gomyai.uk/blog/qwen2-0-5b-instruct/</guid><description>Comprehensive technical overview of Qwen2 0.5B Instruct, its WebGPU quantization memory footprint, latency benchmarks, limitations, and best use cases for client-side AI.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Qwen2.5 1.5B Instruct: High-Precision Multilingual AI for In-Browser Processing</title><link>https://gomyai.uk/blog/qwen2-5-1-5b-instruct/</link><guid isPermaLink="true">https://gomyai.uk/blog/qwen2-5-1-5b-instruct/</guid><description>Detailed technical breakdown of Alibaba Cloud&apos;s Qwen2.5 1.5B Instruct model, WebGPU memory requirements, benchmark capabilities, limitations, and top applications.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Transformers.js &amp; DistilBERT: High-Speed WASM AI Inference in Any Web Browser</title><link>https://gomyai.uk/blog/transformers-js-distilbert/</link><guid isPermaLink="true">https://gomyai.uk/blog/transformers-js-distilbert/</guid><description>Learn how Hugging Face&apos;s Transformers.js and DistilBERT SST-2 enable fast, cross-browser WebAssembly AI inference on CPU and GPU without WebGPU requirements.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Demystifying WebGPU &amp; Hugging Face Transformers.js</title><link>https://gomyai.uk/blog/webgpu-transformers-guide/</link><guid isPermaLink="true">https://gomyai.uk/blog/webgpu-transformers-guide/</guid><description>A technical deep dive into running browser-accelerated machine learning models with Wasm fallbacks.</description><pubDate>Thu, 30 Jul 2026 00:00:00 GMT</pubDate></item></channel></rss>