Ollama Library · phi2
Can I run dolphin-phi?
2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
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 contextdolphin-phi 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 |
|---|---|---|---|
| dolphin-phi:2.7b2.7B parameters (tag)2K documented maximum contextThe displayed memory scenario exceeds this build's supported context.Build sourceCatalog checked 2026-10-13 | Q4_0 | 1.5 GB | ~3.3 GB |
| dolphin-phi:2.7b-v2.6-q4_K_M2.7B parameters (tag)2K documented maximum contextThe displayed memory scenario exceeds this build's supported context.Build sourceCatalog checked 2026-10-13 | Q4_K_M | 1.7 GB | ~3.4 GB |
| dolphin-phi:2.7b-v2.6-q5_K_M2.7B parameters (tag)2K documented maximum contextThe displayed memory scenario exceeds this build's supported context.Build sourceCatalog checked 2026-10-13 | Q5_K_M | 1.9 GB | ~3.7 GB |
| dolphin-phi:2.7b-v2.6-q6_K2.7B parameters (tag)2K documented maximum contextThe displayed memory scenario exceeds this build's supported context.Build sourceCatalog checked 2026-10-13 | Q6_K | 2.1 GB | ~3.9 GB |
| dolphin-phi:2.7b-v2.6-q8_02.7B parameters (tag)2K documented maximum contextThe displayed memory scenario exceeds this build's supported context.Build sourceCatalog checked 2026-10-13 | Q8_0 | 2.8 GB | ~4.6 GB |
Showing the 5 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 dolphin-phi locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull dolphin-phi:2.7b - 3.Check the source for the build's task. For text generation, run
ollama run dolphin-phi:2.7b. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about dolphin-phi
- How much VRAM do I need to run dolphin-phi?
- At 4K context, the smallest published build of dolphin-phi (Q4_0) needs roughly 3.3 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 dolphin-phi without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 3.3 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 dolphin-phi download?
- The smallest published build is 1.5 GB. There are 5 builds in total, the largest being 2.8 GB. Leave some extra free disk space beyond the download itself.
- How do I run dolphin-phi locally?
- Install Ollama, then download a specific build with "ollama pull dolphin-phi:2.7b". 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 dolphin-phi 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