Alibaba Cloud · qwen2
Can I run qwq?
QwQ is the reasoning model of the Qwen series.
Parameter counts and memory belong to each build below. A family can contain several sizes and tasks; fitting in memory is not a quality ranking.
Calculate memory for a build and contextqwq 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.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| qwq:32b-preview-q4_K_M32B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 18.5 GB | ~21.4 GB |
| qwq:32b32B parameters (tag)40K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 18.5 GB | ~21.4 GB |
| qwq:32b-preview-q8_032B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 32.4 GB | ~36.4 GB |
| qwq:32b-q8_032B parameters (tag)40K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 32.4 GB | ~36.4 GB |
| qwq:32b-preview-fp1632B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 61.0 GB | ~67.3 GB |
| qwq:32b-fp1632B parameters (tag)40K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 61.0 GB | ~67.3 GB |
Showing the 6 smallest non-alias builds. Choose any build and change the context. A context above the build's documented maximum is a hypothetical calculation, not a supported setting.
How to run qwq locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull qwq:32b-preview-q4_K_M - 3.Check the source for the build's task. For text generation, run
ollama run qwq:32b-preview-q4_K_M. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
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 21.4 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?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 21.4 GB at 4K context, plus headroom for your operating system. Check the build's runtime requirements. We have not measured its speed on your CPU.
- 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 download a specific build with "ollama pull qwq:32b-preview-q4_K_M". For a build that supports text generation, use ollama run with the same tag. Check the model source for its task and prompt format.
Will qwq run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Compare with similar models
Or start from your memory: 8 GB VRAM, 12 GB VRAM, 16 GB VRAM, 24 GB VRAM or a 16 GB Mac.
Model data from the official Ollama registry · verified 13/10/2026