a2go

Use open weight models (LLM, image, audio) with open source agents on Mac, Linux, and Windows.

Add a new model to the a2go registry — both GGUF (Linux/Windows) and MLX (macOS) variants, with full testing on Runpod.

Generate images from text prompts using the local FLUX.2 model on the GPU.

Transcribe speech audio to text using the local LFM2.5 model on the GPU.

Convert text to speech audio using the local LFM2.5 model on the GPU.