yzma

Go with your own intelligence - local inference in Go using llama.cpp including hardware acceleration

Get Started Try it in your browser See the code

yzma lets you write Go applications that use llama.cpp for local inference.

Your models run in the same process as your program. No model server is necessary. No C compiler is necessary. Use the hardware acceleration that your machine has.

Accelerate

Use CUDA, Metal, Vulkan, ROCm, or WebGPU for maximum performance.

See

Run Vision Language Models on images, audio, and video.

Run anywhere

Run on Linux, macOS, Windows, or in a browser with WebAssembly.

See it run, now

A model in your browser. No install, no signup, and no server.

The page downloads the model one time and then runs it on your machine. Chrome and Edge use the GPU with WebGPU.

Try it in your browser

Powered by yzma

These projects build on yzma.

Kronk

High-performance OpenAI compatible API with both local SDK and model server.

NornicDB

Graph database for AI agents and knowledge systems.

OpenOcta

Desktop IT operations agent for Windows and macOS.

Talking Heads From The Year 2053

First show whose actors use Physical AI running locally on Arduino UNO Q.

See more projects that use yzma

yzma uses the purego and ffi packages, so CGo is not necessary. Build your programs with the normal go build and go run commands.

Ready to get started? Click here.