Written by Jakub Rusinowski · Last updated July 10, 2026
The world's most transparent LLM. OLMo 2 releases everything: weights, training code, training data, evaluation suite, and intermediate checkpoints. Perfect for researchers and compliance-sensitive deployments needing fully auditable AI. Competitive with Llama 3.1 on most benchmarks.
| OLMo 2 7B Instruct | Min 5 GB VRAM · Q4_K_M · 4,096 ctx · ollama run olmo2:7b |
| OLMo 2 13B Instruct | Min 9 GB VRAM · Q4_K_M · 4,096 ctx · ollama run olmo2:13b |
The cheapest GPU that runs OLMo 2 locally (min 5 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run olmo2:7b
Minimum VRAM: 5 GB. For best results use Q4_K_M quantization.
OLMo 2 needs about 5 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: OLMo 2 7B Instruct (5 GB, Q4_K_M); OLMo 2 13B Instruct (9 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — OLMo 2 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 2 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.
Install Ollama, then run: ollama run olmo2:7b. This downloads OLMo 2 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.