Allen Institute for AI · olmo3
Can I run olmo-3.1?
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
32.2B parameters64K contexttextApache License6 builds
olmo-3.1 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 |
|---|---|---|---|
| olmo-3.1:32b | Q4_K_M | 18.1 GB | ~26.3 GB(est.) |
| olmo-3.1:32b-instruct-q4_K_M | Q4_K_M | 18.1 GB | ~26.3 GB(est.) |
| olmo-3.1:32b-think-q8_0 | Q8_0 | 31.9 GB | ~46.0 GB(est.) |
| olmo-3.1:32b-instruct-q8_0 | Q8_0 | 31.9 GB | ~46.0 GB(est.) |
| olmo-3.1:32b-think-fp16 | F16 | 60.0 GB | ~86.3 GB(est.) |
| olmo-3.1:32b-instruct-fp16 | F16 | 60.0 GB | ~86.3 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 olmo-3.1 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run olmo-3.1:32b - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about olmo-3.1
- How much VRAM do I need to run olmo-3.1?
- At 4K context, the smallest published build of olmo-3.1 (Q4_K_M) needs roughly 26.3 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 olmo-3.1 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 26.3 GB of free RAM for the smallest build.
- How big is the olmo-3.1 download?
- The smallest published build is 18.1 GB. There are 6 builds in total, the largest being 60.0 GB. Leave some extra free disk space beyond the download itself.
- How do I run olmo-3.1 locally?
- Install Ollama, then run "ollama run olmo-3.1:32b" in a terminal. The weights download on first use and an interactive session opens.
Will olmo-3.1 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