Can gpt-oss Safeguard 120B run on the 2x RTX 5090?
Yes. At 8K context the best fit is Q8_0, using about 60.1 GB of the 60.8 GB usable on the 2x RTX 5090. Estimated speed ceiling: ~574 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 59.2 GB Tight | 59.3 GB Tight | 60.2 GB Tight | 63.6 GB No | 582 |
| 3-bit (Q3_K_M) • | 59.3 GB Tight | 59.4 GB Tight | 60.2 GB Tight | 63.6 GB No | 581 |
| 4-bit (Q4_K_M) • | 59.4 GB Tight | 59.5 GB Tight | 60.4 GB Tight | 63.7 GB No | 580 |
| 5-bit (Q5_K_M) • | 59.5 GB Tight | 59.6 GB Tight | 60.5 GB Tight | 63.9 GB No | 579 |
| 6-bit (Q6_K) • | 59.9 GB Tight | 60.0 GB Tight | 60.9 GB No | 64.2 GB No | 575 |
| 8-bit (Q8_0) • | 60.0 GB Tight | 60.1 GB Tight | 60.9 GB No | 64.3 GB No | 574 |
| 16-bit (F16/BF16) | 219 GB No | 219 GB No | 220 GB No | 223 GB No | — |
• real GGUF file size from unsloth/gpt-oss-safeguard-120b-GGUF. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs gpt-oss Safeguard 120B: this card, the 2x RTX 5090 (2× 32 GB, launch MSRP $3,998) at Q8_0, fully in VRAM at 8K context.
- Largest popular model that fits the 2x RTX 5090: Qwen3.6 35B A3B (36B, MoE) at Q8_0, about 36.2 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
gpt-oss Safeguard 120B on every GPU and Mac · Every model that runs on the 2x RTX 5090 · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (openai/gpt-oss-safeguard-120b), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.