Loading…
Loading…
Models / gpt-oss
2 models (20B to 120B) · ↓ 9.3M downloads a month · from $0.18/h on 2x RTX 3060 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 |
|---|---|---|---|---|
| Originalopenai/gpt-oss-20b | vLLM | 14 GB | 18 GB | $0.18/h 2x RTX 3060 |
| gpt oss safeguard 20bopenai/gpt-oss-safeguard-20b | vLLM | 14 GB | 18 GB | $0.18/h 2x RTX 3060 |
| unsloth bnb 4bit (unsloth)unsloth/gpt-oss-20b-unsloth-bnb-4bit | vLLM | 13 GB | 16.6 GB | $0.18/h 2x RTX 3060 |
| Main (unsloth)unsloth/gpt-oss-20b | vLLM | 14 GB | 18 GB | $0.18/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalopenai/gpt-oss-120b | vLLM | 65 GB | 75.4 GB | $0.89/h 2x Nvidia A40 |
| gpt oss safeguard 120bopenai/gpt-oss-safeguard-120b | vLLM | 65 GB | 75.4 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").