Google DeepMind · gemma
Can I run codegemma?
CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.
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 contextcodegemma 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 |
|---|---|---|---|
| codegemma:2b2B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 1.4 GB | ~2.0 GB |
| codegemma:2b-code-q4_02B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 1.4 GB | ~2.0 GB |
| codegemma:2b-code-q4_K_M2B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 1.5 GB | ~2.1 GB |
| codegemma:2b-code-v1.1-q4_K_M2B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 1.5 GB | ~2.1 GB |
| codegemma:2b-code-q5_K_M2B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 1.7 GB | ~2.3 GB |
| codegemma:2b-code-v1.1-q5_K_M2B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 1.7 GB | ~2.3 GB |
| codegemma:2b-code-q6_K2B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q6_K | 1.9 GB | ~2.5 GB |
| codegemma:2b-code-v1.1-q6_K2B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q6_K | 1.9 GB | ~2.5 GB |
Showing the 8 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 codegemma locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull codegemma:2b - 3.Check the source for the build's task. For text generation, run
ollama run codegemma:2b. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about codegemma
- How much VRAM do I need to run codegemma?
- At 4K context, the smallest published build of codegemma (Q4_0) needs roughly 2.0 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 codegemma without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 2.0 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 codegemma download?
- The smallest published build is 1.4 GB. There are 30 builds in total, the largest being 15.9 GB. Leave some extra free disk space beyond the download itself.
- How do I run codegemma locally?
- Install Ollama, then download a specific build with "ollama pull codegemma:2b". 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 codegemma 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