Allen Institute for AI · olmo2
Can I run olmo2?
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.
7.3B parameters4K contexttextApache License6 builds
olmo2 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 |
|---|---|---|---|
| olmo2:7b | Q4_K_M | 4.2 GB | ~6.3 GB(est.) |
| olmo2:7b-1124-instruct-q8_0 | Q8_0 | 7.2 GB | ~10.7 GB(est.) |
| olmo2:13b | Q4_K_M | 7.8 GB | ~11.5 GB(est.) |
| olmo2:13b-1124-instruct-q8_0 | Q8_0 | 13.6 GB | ~19.8 GB(est.) |
| olmo2:7b-1124-instruct-fp16 | F16 | 13.6 GB | ~19.8 GB(est.) |
| olmo2:13b-1124-instruct-fp16 | F16 | 25.6 GB | ~36.9 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 olmo2 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run olmo2:7b - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about olmo2
- How much VRAM do I need to run olmo2?
- At 4K context, the smallest published build of olmo2 (Q4_K_M) needs roughly 6.3 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 olmo2 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 6.3 GB of free RAM for the smallest build.
- How big is the olmo2 download?
- The smallest published build is 4.2 GB. There are 6 builds in total, the largest being 25.6 GB. Leave some extra free disk space beyond the download itself.
- How do I run olmo2 locally?
- Install Ollama, then run "ollama run olmo2:7b" in a terminal. The weights download on first use and an interactive session opens.
Will olmo2 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