Will this model run on your hardware?
Can I run OpenAI: gpt-oss-safeguard-20b locally?
- 22B parameters (3.6B active, MoE)
- context up to 128K
- licence: apache-2.0
- Weights: openai/gpt-oss-safeguard-20b · GGUF: unsloth/gpt-oss-safeguard-20b-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q6_K | 12.0 GB |
| Q5_K_M | 11.7 GB |
| Q4_K_M | 11.6 GB |
| Q3_K_M | 11.5 GB |
| Q2_K | 11.5 GB |
Run it locally
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_M
llama serve -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_M
LM Studio: open unsloth/gpt-oss-safeguard-20b-GGUF