Machine Learning Run Bonsai 27B on Your Phone: 1-Bit Local AI
Run the first 27B-class model on a phone: MLX, llama.cpp, tool calls, and the memory math.
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Machine Learning Run the first 27B-class model on a phone: MLX, llama.cpp, tool calls, and the memory math.
Tutorials Meituan's 1.6T open MoE topped OpenRouter as 'Owl Alpha.' Call it in Python with the OpenAI SDK.
Tutorials Turn a still image into a 720p video with native audio using xAI's Grok Imagine 1.5 in Python.
Tutorials Control thinking_level, media_resolution and thought signatures in the Gemini 3.1 Pro API.
Tutorials Compile llama.cpp with Vulkan in Termux and run a quantized LLM on your Android GPU, no root.
Tutorials Deploy Microsoft's new reasoning model and build a tool-calling triage agent.
Tutorials Call Microsoft's June 2 coding model via OpenRouter for cheap, fast refactors.
Tutorials Install grok-build-0.1, run plan mode, stream JSON in CI, and call the API from Python.
Tutorials Build a research-write-review multi-agent pipeline using Microsoft Agent Framework 1.0 in Python.
Tutorials Generate AI video in Python with Veo 3.1 — the model powering Google's Omni Flash launch.
DevOps Ingress-NGINX hit EOL in 2026. Convert to Gateway API with ingress2gateway 1.0.
Tutorials Cut LangGraph checkpoint storage 41x with DeltaChannel - new in 1.2.