I tested 3 local LLMs for UI design work, and only one of them behaved like a real designer

AMD's most exciting AI machine this year isn't a GPU — it's a $3,999 mini PC

AMD's Ryzen AI Halo Developer Platform is a $3,999 mini PC powered by the Ryzen AI Max+ 395 APU with 128GB of unified memory, targeting local AI professionals who need to run massive LLMs without discrete GPU constraints. It can handle 200B parameter models, outpacing even the RTX 5090 in raw model capacity, while undercutting Nvidia's competing DGX Spark (now $4,699) on price. The machine ships with AMD's Ryzen AI Developer Center pre-configured, reducing the historically painful ROCm setup. However, ROCm still lags behind CUDA in maturity — Ollama can still require manual GPU path configuration, and quantization library support arrives later than on CUDA. AMD's upcoming Gorgon Halo platform promises 192GB of unified memory and 300B parameter model support, but closing the software gap with Nvidia remains the key challenge.

Engineering managers ditch cloud AI for local LLMs

Engineering managers are increasingly turning to local LLMs as a third option between expensive cloud AI licences and legal restrictions on data governance. The trend gained credibility when Georgi Gerganov, creator of llama.cpp, publicly endorsed using a Qwen3-27B model locally for daily coding tasks. Former Meta/Google DeepMind VP Mat Velloso is also switching to open-weight models, citing concerns about reliance on proprietary models that could be withdrawn without notice. Local models are seen as already capable enough for routine tasks like autocomplete, refactoring, documentation, and test generation, especially where latency, privacy, or cost predictability matter more than peak capability.

Adobe to acquire Topaz Labs for AI enhancement

Adobe has signed a definitive agreement to acquire Topaz Labs, the Emmy-winning AI image and video enhancement company behind tools like Topaz Photo, Topaz Video, and Topaz Gigapixel. The deal brings upscaling, noise reduction, frame interpolation, and footage restoration capabilities into Adobe's Firefly, Photoshop, Lightroom, and Premiere ecosystem. A key asset is Neurostream, Topaz Labs' technology for running large AI models locally on consumer devices, aligning Adobe with the industry push toward on-device AI. The acquisition is partly defensive — removing a strong enhancement competitor from the market and securing a durable layer of AI creativity that outlasts any single generative model. Topaz Labs will continue operating as a standalone product line, with CEO Eric Yang staying on. The deal awaits regulatory approval and is expected to close in the second half of 2026.

Design Systems, Tokens and AI

AI is reshaping how design systems are built and maintained by automating the generation of design token sets from natural language descriptions. Rather than manually defining hundreds of CSS custom property values, teams can describe a desired aesthetic and let AI produce a complete, internally consistent token hierarchy covering global, alias, and component-specific tokens. Progress ThemeBuilder is used as a practical example, demonstrating how AI-generated tokens can be exported as CSS or SASS and consumed directly by component libraries. The token layer acts as a contract between AI tooling and components, enabling mixed workflows where AI-generated baselines are refined with manual overrides. For enterprise teams, this compresses the time between brand decisions and implementation while keeping governance in human hands.

Using Visual Studio Code’s ‘air-gapped’ AI model mode

VS Code 1.122 bổ sung chế độ BYOK cho phép dùng LLM cục bộ hoặc nhà cung cấp bên thứ ba (như LM Studio) cho chat, tools và MCP servers mà không cần đăng nhập GitHub. Người dùng chỉ có thể sử dụng các model có VRAM 8GB (Gemma4 2B, Qwen3.5 9B, Codestral 22B) cho chat và tác vụ tiện ích, chứ không hỗ trợ inline code completions hay gợi ý chỉnh sửa. Muốn khắc phục hạn chế này, người dùng phải cài extension của bên thứ ba như Continue.

Lập trình viên muốn tự chủ về dữ liệu và tránh phụ thuộc vào cloud AI mà không cần phụ thuộc vào các dịch vụ bên ngoài như GitHub, nên tìm hiểu cách sử dụng BYOK mode trong VS Code để tích hợp các mô hình AI cá nhân hóa, đặc biệt khi công nghệ này hỗ trợ chat, công cụ và MCP mà không cần đăng nhập.

Shaping Stories into Experience: The Work of Kevin Lam

A designer spotlight on Kevin Lam (urfd), a Brisbane-based brand and digital designer at Nightjar Studio. Kevin shares five featured projects — including a medical aesthetics clinic, a photographer's portfolio, a real estate brand, a natural event documentary site, and a lifestyle precinct — each built around translating brand stories into soulful digital and visual experiences. He also covers his design philosophy (curiosity, finding a north star, caring about craft, collaboration) and his toolset including Figma, Cinema 4D, After Effects, Cavalry, and Photoshop.

Skip the cloud: this compact Ryzen AI 9 mini PC handles 8B local LLMs and it's at a special Prime Day price

The GEEKOM A9 Max mini PC is on sale for $1,189.15 during Prime Day. It features an AMD Ryzen AI 9 HX 370 processor, 32GB DDR5 RAM, 1TB SSD, and Windows 11 Pro in a compact form factor. The 32GB RAM makes it capable of running 7B–8B local LLMs via tools like Ollama or LM Studio without relying on cloud services. It supports up to 128GB RAM and dual PCIe Gen4 SSDs up to 8TB, offering room to grow. Connectivity includes Wi-Fi 7, USB 4, dual 2.5 GbE, and HDMI 2.1. It's positioned as a compact developer workstation or home lab machine for those wanting to experiment with local AI.