Ollama Library · llama
Can I run megadolphin?
MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.
120B parameters4K contexttextLLAMA 2 COMMUNITY LICENSE AGREEMENT6 builds
megadolphin 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 |
|---|---|---|---|
| megadolphin:120b | Q4_0 | 63.1 GB | ~90.6 GB(est.) |
| megadolphin:120b-v2.2-q4_K_M | Q4_K_M | 67.2 GB | ~96.5 GB(est.) |
| megadolphin:120b-v2.2-q5_K_M | Q5_K_M | 79.2 GB | ~113.6 GB(est.) |
| megadolphin:120b-v2.2-q6_K | Q6_K | 91.9 GB | ~131.8 GB(est.) |
| megadolphin:120b-v2.2-q8_0 | Q8_0 | 119.1 GB | ~170.7 GB(est.) |
| megadolphin:120b-v2.2-fp16 | F16 | 224.1 GB | ~320.9 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run megadolphin locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run megadolphin:120b - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about megadolphin
- How much VRAM do I need to run megadolphin?
- At 4K context, the smallest published build of megadolphin (Q4_0) needs roughly 90.6 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 megadolphin without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 90.6 GB of free RAM for the smallest build.
- How big is the megadolphin download?
- The smallest published build is 63.1 GB. There are 6 builds in total, the largest being 224.1 GB. Leave some extra free disk space beyond the download itself.
- How do I run megadolphin locally?
- Install Ollama, then run "ollama run megadolphin:120b" in a terminal. The weights download on first use and an interactive session opens.
Will megadolphin run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026