Ollama Library · llama
Can I run dolphin-llama3?
Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.
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-llama3 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-llama3:8b-256k-v2.9-q4_08B parameters (tag)250K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 4.3 GB | ~5.6 GB |
| dolphin-llama3:8b8B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 4.3 GB | ~5.6 GB |
| dolphin-llama3:8b-256k-v2.9-q4_K_M8B parameters (tag)250K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 4.6 GB | ~5.8 GB |
| dolphin-llama3:8b-v2.9-q4_K_M8B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 4.6 GB | ~5.8 GB |
| dolphin-llama3:8b-256k-v2.9-q5_K_M8B parameters (tag)250K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 5.3 GB | ~6.7 GB |
| dolphin-llama3:8b-v2.9-q5_K_M8B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 5.3 GB | ~6.7 GB |
| dolphin-llama3:8b-256k-v2.9-q6_K8B parameters (tag)250K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q6_K | 6.1 GB | ~7.5 GB |
| dolphin-llama3:8b-v2.9-q6_K8B parameters (tag)8K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q6_K | 6.1 GB | ~7.5 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 dolphin-llama3 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull dolphin-llama3:8b-256k-v2.9-q4_0 - 3.Check the source for the build's task. For text generation, run
ollama run dolphin-llama3:8b-256k-v2.9-q4_0. 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-llama3
- How much VRAM do I need to run dolphin-llama3?
- At 4K context, the smallest published build of dolphin-llama3 (Q4_0) needs roughly 5.6 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-llama3 without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 5.6 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-llama3 download?
- The smallest published build is 4.3 GB. There are 18 builds in total, the largest being 131.4 GB. Leave some extra free disk space beyond the download itself.
- How do I run dolphin-llama3 locally?
- Install Ollama, then download a specific build with "ollama pull dolphin-llama3:8b-256k-v2.9-q4_0". 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-llama3 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