Can I run qwq?

qwq 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 qwq locally

1. 1.Install Ollama for Windows, macOS or Linux.
2. 2.Run this in a terminal:ollama run qwq:32b-preview-q4_K_M
3. 3.The weights download on first run, then an interactive prompt opens.

Frequently asked questions about qwq

How much VRAM do I need to run qwq?

At 4K context, the smallest published build of qwq (Q4_K_M) needs roughly 26.8 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 qwq 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 26.8 GB of free RAM for the smallest build.

How big is the qwq download?

The smallest published build is 18.5 GB. There are 6 builds in total, the largest being 61.0 GB. Leave some extra free disk space beyond the download itself.

How do I run qwq locally?

Install Ollama, then run "ollama run qwq:32b-preview-q4_K_M" in a terminal. The weights download on first use and an interactive session opens.