Alibaba Cloud · qwen3moe
Can I run qwen3-coder?
Alibaba's performant long context models for agentic and coding tasks.
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 contextqwen3-coder 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 |
|---|---|---|---|
| qwen3-coder:30b30B parameters (tag)256K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 17.3 GB | ~19.4 GB |
| qwen3-coder:30b-a3b-q8_030B parameters (tag)256K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 30.3 GB | ~33.4 GB |
| qwen3-coder:30b-a3b-fp1630B parameters (tag)256K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 56.9 GB | ~62.2 GB |
| qwen3-coder:480b480B parameters (tag)256K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 270.1 GB | ~293.1 GB |
| qwen3-coder:480b-a35b-q8_0480B parameters (tag)256K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 475.3 GB | ~514.7 GB |
| qwen3-coder:480b-a35b-fp16480B parameters (tag)256K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 894.5 GB | ~967.4 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 qwen3-coder locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull qwen3-coder:30b - 3.Check the source for the build's task. For text generation, run
ollama run qwen3-coder:30b. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about qwen3-coder
- How much VRAM do I need to run qwen3-coder?
- At 4K context, the smallest published build of qwen3-coder (Q4_K_M) needs roughly 19.4 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 qwen3-coder without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 19.4 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 qwen3-coder download?
- The smallest published build is 17.3 GB. There are 6 builds in total, the largest being 894.5 GB. Leave some extra free disk space beyond the download itself.
- How do I run qwen3-coder locally?
- Install Ollama, then download a specific build with "ollama pull qwen3-coder:30b". 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 qwen3-coder 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