Microsoft · phi3
Can I run phi4-mini?
Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
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 contextphi4-mini 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 |
|---|---|---|---|
| phi4-mini:3.8b3.8B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 2.3 GB | ~3.4 GB |
| phi4-mini:3.8b-q8_03.8B parameters (tag)4K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 3.8 GB | ~5.0 GB |
| phi4-mini:3.8b-fp163.8B parameters (tag)4K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 7.2 GB | ~8.6 GB |
Showing the 3 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 phi4-mini locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull phi4-mini:3.8b - 3.Check the source for the build's task. For text generation, run
ollama run phi4-mini:3.8b. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about phi4-mini
- How much VRAM do I need to run phi4-mini?
- At 4K context, the smallest published build of phi4-mini (Q4_K_M) needs roughly 3.4 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 phi4-mini without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 3.4 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 phi4-mini download?
- The smallest published build is 2.3 GB. There are 3 builds in total, the largest being 7.2 GB. Leave some extra free disk space beyond the download itself.
- How do I run phi4-mini locally?
- Install Ollama, then download a specific build with "ollama pull phi4-mini:3.8b". 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 phi4-mini 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