An experimental Qwen3.8 architecture preview for an Apple silicon Mac with a large amount of unified memory. This specific local download uses MLX and is an advanced optional choice.
Where it works well
- A local Qwen3.8 architecture preview.
- Image and text understanding.
- Mixture-of-experts design for coding, tool use, and reasoning.
Common use cases
- Compare local coding results with a smaller model.
- Review a diagram alongside technical notes.
- Explore a multi-step task through a compatible app.
Know its limits
- This 125b-mlx tag requires Apple silicon and MLX support. It is not a Windows or generic GGUF download.
- The 105 GB download includes a large memory footprint despite sparse activation. This experimental release needs ample headroom and a compatible current runtime.
Run it on your computer
Compatibility: Apple silicon Mac · MLX runtime only
Start with a compressed download and a short conversation. Our estimate is about 192 GB of total RAM or Mac unified memory, with room for the operating system. The listed 105 GB download is the model file, not its full running memory use.
Check the model’s supported runtime and hardware before loading it. System RAM on a PC and unified memory on a Mac are different from dedicated NVIDIA VRAM. A memory match doesn’t guarantee compatibility or speed. Choose a smaller model if responses are too slow.
Use a desktop app that supports the listed model format, such as LM Studio or Ollama. Download the exact local variant, load it in Chat, and start with one small task. Model downloads need internet; local chat can work offline once the model is downloaded.
Official model information
Model capabilities checked October 2026. The use cases above are practical starting suggestions, not performance guarantees.