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

Can gpt-oss 20B run on the RTX 4060 Ti 16GB?

Yes. At 8K context the best fit is Q8_0, using about 12.3 GB of the 15.2 GB usable on the RTX 4060 Ti 16GB. Estimated speed ceiling: ~119 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.6 GB Fits11.7 GB Fits12.3 GB Fits14.6 GB Tight124
3-bit (Q3_K_M) •11.6 GB Fits11.7 GB Fits12.3 GB Fits14.6 GB Tight124
4-bit (Q4_K_M) •11.8 GB Fits11.8 GB Fits12.4 GB Fits14.7 GB Tight123
5-bit (Q5_K_M) •11.8 GB Fits11.9 GB Fits12.5 GB Fits14.7 GB Tight122
6-bit (Q6_K) •12.1 GB Fits12.2 GB Fits12.8 GB Fits15.0 GB Tight119
8-bit (Q8_0) •12.2 GB Fits12.3 GB Fits12.8 GB Fits15.1 GB Tight119
16-bit (F16/BF16) •13.7 GB Tight13.8 GB Tight14.4 GB Tight16.6 GB No104

• real GGUF file size from bartowski/openai_gpt-oss-20b-GGUF. Speed is a bandwidth ceiling (288 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 20B on every GPU and Mac · Every model that runs on the RTX 4060 Ti 16GB · Other models that fit 16 GB VRAM · 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-20b), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.