Models

Akio uses a curated whitelist of models to ensure every supported model works reliably with all features — including tools, MCP, orchestration and more. Rather than allowing arbitrary models, whitelisting lets us guarantee compatibility and a consistent experience across the board.

All models are hosted on Hugging Face and served in GGUF format.

Model	Repo	Parameters	Tags
Qwen3-0.6B	Fastiraz/Qwen3-0.6B-GGUF	0.6B	llm
Qwen3-1.7B	Fastiraz/Qwen3-1.7B-GGUF	1.7B	llm
Qwen3-4B	Fastiraz/Qwen3-4B-GGUF	4B	llm
Qwen3-8B	Fastiraz/Qwen3-8B-GGUF	8B	llm
Qwen3-14B	Fastiraz/Qwen3-14B-GGUF	14B	llm
Qwen3-32B	Fastiraz/Qwen3-32B-GGUF	32B	llm
Qwen3-Embedding-0.6B	Fastiraz/Qwen3-Embedding-0.6B-GGUF	0.6B	embedding
Z-Image-Turbo	Tongyi-MAI/Z-Image-Turbo		image

Start with a smaller model like ggml-org/Qwen3-0.6B-GGUF for faster testing on CPU. You can also start with the Z-Image-Turbo model for the fastest image generation testing.