gpt-oss-20b
OpenAI- Mixture of experts, 3.6B active
- Apache-2.0
- Released in 4-bit
- Estimated
openai/gpt-oss-20b on Hugging Face
gpt-oss-20b with Glyd
| As released | Glyd | Change, % | ||
|---|---|---|---|---|
| Weights in GPU memory, GB4-bit weights counted as they are | 13.76 | 12.58est. | −9 | |
| Smallest single GPU, GBWeights, an 8K-token KV cache and 1.5 GB for the runtime | 16 | 16 | ||
| H100 80 GB GPUs it takes | 1 | 1 |
Which single GPU it fits
4-bit weights counted as they are.
| Memory | GPUs | As released | Glyd |
|---|---|---|---|
| 16 GB | RTX 4080, RTX 5080 | Fits | Fits |
| 24 GB | RTX 4090, RTX 3090, A10 | Fits | Fits |
| 32 GB | RTX 5090 | Fits | Fits |
| 48 GB | RTX A6000, L40S, RTX 6000 Ada | Fits | Fits |
| 80 GB | H100, A100 80 GB | Fits | Fits |
| 96 GB | RTX PRO 6000, GH200 | Fits | Fits |
| 141 GB | H200 | Fits | Fits |
Related models
Measured so far
Twenty-two open models measured, with quality wherever bf16 fits one GPU.