§01·model · /models
gpt-oss 20B
llmactive
§02·GPUs that run this model
10 total| GPU | VRAM | Series | Best speed | Min VRAM | Works | Benchmarks | |
|---|---|---|---|---|---|---|---|
| RTX 4080 Super | 16GB | 40 | 6364prefill tokens/s | 16GB | ✓ | 1 | check ↗ |
| RTX 5090 | 32GB | 50 | 298.2tokens/s | ✓ | 3 | check ↗ | |
| RTX 5080 | 16GB | 50 | 172.4tokens/s | 16GB | ✓ | 2 | check ↗ |
| RTX 3090 Ti | 24GB | 30 | 160.3tokens/s | 24GB | ✓ | 2 | check ↗ |
| RTX 5070 Ti | 16GB | 50 | 156tokens/s | 16GB | ✓ | 2 | check ↗ |
| RTX 3090 | 24GB | 30 | 147.5tokens/s | 24GB | ✓ | 2 | check ↗ |
| RTX 4080 | 16GB | 40 | 136.5tokens/s | 16GB | ✓ | 2 | check ↗ |
| RTX 4070 Ti Super | 16GB | 40 | 128.9tokens/s | 16GB | ✓ | 2 | check ↗ |
| RTX 5060 Ti | 16GB | 50 | 92.1tokens/s | 16GB | ✓ | 2 | check ↗ |
| RTX 4060 Ti 16GB | 16GB | 40 | 63.2tokens/s | 16GB | ✓ | 2 | check ↗ |