Written by Jakub Rusinowski · Last updated September 19, 2026
Fully open, not just open-weight: Ai2 publishes the weights, the training data (Dolma 3), the code and the intermediate checkpoints under Apache-2.0. Base, Instruct and Think variants at each size, which makes this the family to reach for when the training process itself has to be auditable.
| Licence | What it permits | Applies to |
|---|---|---|
Apache-2.0 | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | Olmo 3 7B, Olmo 3 32B |
| Olmo 3 7B | Min 5 GB VRAM · Q4_K_M · 65,536 ctx · |
| Olmo 3 32B | Min 20 GB VRAM · Q4_K_M · 65,536 ctx · |
The cheapest GPU that runs Olmo 3 locally (min 5 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run olmo-3
Minimum VRAM: 5 GB. For best results use Q4_K_M quantization.
Olmo 3 needs about 5 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Olmo 3 7B (5 GB, Q4_K_M); Olmo 3 32B (20 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Olmo 3 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Olmo 3 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Olmo 3 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.