A high-memory option for coding, reasoning, and document images. This October 2026 listing is for users who already have a capable machine and can check runtime compatibility.
Where it works well
- Image and document-page understanding.
- Coding and reasoning in one model.
- Structured tool-oriented tasks.
Common use cases
- Discuss a chart with its source notes.
- Review code with a UI screenshot.
- Extract visible information from a document page.
Know its limits
- New architecture and quantization support varies by runtime and GPU; a RAM estimate is not a compatibility guarantee.
- The default 80–90 GB download is demanding; CPU-only use and long context can be impractical.
Run it on your computer
Compatibility: New runtime support: check your app and GPU before downloading.
Start with a compressed download and a short conversation. Our estimate is about 128 GB of total RAM or Mac unified memory, with room for the operating system. The listed 80–90 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.