RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can gpt-oss 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

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •59.3 GB Tight59.5 GB Tight60.3 GB Tight63.7 GB No581
3-bit (Q3_K_M) •59.3 GB Tight59.5 GB Tight60.3 GB Tight63.7 GB No581
4-bit (Q4_K_M) •59.5 GB Tight59.6 GB Tight60.4 GB Tight63.8 GB No579
5-bit (Q5_K_M)78.5 GB No78.6 GB No79.4 GB No82.8 GB No—
6-bit (Q6_K) •59.9 GB Tight60.0 GB Tight60.9 GB No64.2 GB No575
8-bit (Q8_0) •60.0 GB Tight60.1 GB Tight60.9 GB No64.3 GB No574
16-bit (F16/BF16) •61.8 GB No61.9 GB No62.8 GB No66.2 GB No—

• real GGUF file size from bartowski/openai_gpt-oss-120b-GGUF. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.

What fits instead

"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 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-120b), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.