gpt-oss 20B: VRAM requirements and GPUs that run it

Memory needed by quantization

Totals include about 10% runtime overhead and the KV cache. Its conversation memory (KV cache) is unusually small, so going from 8K to 32K context adds only about 1.1 GB. It is a mixture-of-experts model: 21B parameters in total but only about 3.6B are used for each token, so it runs much faster than a dense model of the same size and stays usable even when part of it sits in system RAM. Most people should download Q4_K_M; Q5 or Q8 only make sense if you have spare memory. Read which quantization to pick.

Which GPUs can run gpt-oss 20B?

16 of the 40 cards we track run it fully in VRAM at 8K context. The cheapest entry point is a 16 GB card such as the RTX 4060 Ti, and the fastest is the RTX 5090 at about 130 tokens per second. 24 more can run it with part of the model in system RAM, which is noticeably slower.

Running it on a Mac

Apple Silicon Macs can give a model about 72% of their unified memory. gpt-oss 20B fits from 16 GB (Apple M1, about 11 tokens per second). With a faster chip like the Apple M3 Ultra (96 GB) expect around 61 tokens per second. Compare the options in our Mac vs NVIDIA guide.

Similar size models: Gemma 3 12B, Mistral Nemo 12B, Phi-4 14B, Qwen3 14B, DeepSeek-R1 Distill 14B.

Compare gpt-oss 20B

Questions

Estimates based on model size, architecture and memory bandwidth. Real numbers vary with software, drivers and context length.