Loading…
Loading…
Models / Olmo-3
1 model (32B) · ↓ 34.3K downloads a month · from $0.89/h on 2x Nvidia A40 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Olmo 3.1 32B Thinkallenai/Olmo-3.1-32B-Think | vLLM | 64 GB | 76.2 GB | $0.89/h 2x Nvidia A40 |
| Olmo 3 32B Thinkallenai/Olmo-3-32B-Think | vLLM | 64 GB | 76.2 GB | $0.89/h 2x Nvidia A40 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").