Can gpt oss safeguard 20b run on the RTX 4070 Super?
No. Even at 2-bit with 8K context, gpt oss safeguard 20b needs about 11.7 GB, more than the 11.4 GB usable on the RTX 4070 Super.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 11.6 GB No | 11.7 GB No | 12.2 GB No | 14.5 GB No | — |
| 3-bit (Q3_K_M) • | 11.6 GB No | 11.7 GB No | 12.3 GB No | 14.5 GB No | — |
| 4-bit (Q4_K_M) • | 11.7 GB No | 11.8 GB No | 12.4 GB No | 14.6 GB No | — |
| 5-bit (Q5_K_M) • | 11.8 GB No | 11.9 GB No | 12.4 GB No | 14.7 GB No | — |
| 6-bit (Q6_K) • | 12.1 GB No | 12.2 GB No | 12.8 GB No | 15.0 GB No | — |
| 8-bit (Q8_0) • | 12.2 GB No | 12.3 GB No | 12.8 GB No | 15.1 GB No | — |
| 16-bit (F16/BF16) • | 13.7 GB No | 13.8 GB No | 14.4 GB No | 16.6 GB No | — |
• real GGUF file size from unsloth/gpt-oss-safeguard-20b-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.
Hardware that does fit it
RTX 4060 Ti 16GBRTX 4070 Ti SuperRTX 4080RTX 4080 SuperRTX 5060 Ti 16GBRTX 5070 Ti
More
gpt oss safeguard 20b on every GPU and Mac · Every model that runs on the RTX 4070 Super · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (openai/gpt-oss-safeguard-20b), NVIDIA specs. Data as of 2026-11-17.