Can I run solar-pro?

solar-pro system requirements

Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.

Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.

How to run solar-pro locally

1. 1.Install Ollama for Windows, macOS or Linux.
2. 2.Run this in a terminal:ollama run solar-pro:22b-preview-instruct-q4_0
3. 3.The weights download on first run, then an interactive prompt opens.

Frequently asked questions about solar-pro

How much VRAM do I need to run solar-pro?

At 4K context, the smallest published build of solar-pro (Q4_0) needs roughly 17.0 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.

Can I run solar-pro without a dedicated GPU?

Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 17.0 GB of free RAM for the smallest build.

How big is the solar-pro download?

The smallest published build is 11.6 GB. There are 6 builds in total, the largest being 41.2 GB. Leave some extra free disk space beyond the download itself.

How do I run solar-pro locally?

Install Ollama, then run "ollama run solar-pro:22b-preview-instruct-q4_0" in a terminal. The weights download on first use and an interactive session opens.