The OpenAI model card says gpt-oss-20b (21B parameters, 3.6B active) runs within 16 GB of memory and gpt-oss-120b (117B, 5.1B active) runs on a single 80 GB GPU (Hugging Face: openai/gpt-oss-120b model card). Both are mixture-of-experts models with few active parameters, so they generate quickly for their size.
| Model | Params (total / active) | Est. memory, Q4 @ 8k ctx | Est. memory, Q8 @ 8k ctx | Cheapest fit in our data (Q4) |
|---|---|---|---|---|
| gpt-oss-20b (MoE) | 21B / 3.6B | 13.7 GB | 24.8 GB | GeForce RTX 5060 Ti 16GB ($429, GPU launch MSRP) |
| gpt-oss-120b (MoE) | 117B / 5.1B | 64.7 GB | 126.8 GB | GMKtec EVO-X2 (128GB / 1TB) ($3,499.99, system, listed price) |
Parameter counts: Hugging Face: openai/gpt-oss-120b model card. Memory figures are our estimates (see methodology), not measurements.
Check your own hardware
Can My PC Run It?
Loading…