gpt-oss 120B has 117B parameters with 5.1B active per token (mixture of experts), 36 layers and 8 KV heads of dimension 64. At the everyday setting, Q4_K_M and 8k context, it needs an estimated 71.7 GB, so the smallest card that fits is 80 GB.
Memory by quantisation and context
| Quant | 4,096 ctx | 8,192 ctx | 32,768 ctx |
|---|---|---|---|
| Q8_0 | 129.8 GB · fits multi-GPU | 130.1 GB · fits multi-GPU | 131.9 GB · fits multi-GPU |
| Q5_K_M | 87.2 GB · fits 96 GB | 87.5 GB · fits 96 GB | 89.3 GB · fits 96 GB |
| Q4_K_M | 71.4 GB · fits 80 GB | 71.7 GB · fits 80 GB | 73.5 GB · fits 80 GB |
Weights at this quant: 67.9 GB at Q4. Every extra 1,000 tokens of context adds about 0.0737 GB of KV cache at FP16. Try other settings in the VRAM calculator.
Speed by GPU, at Q4 and 8k context
| GPU | Memory | Bandwidth | Fits | Est. tokens/s | Feels like |
|---|---|---|---|---|---|
| RTX 3060 12 GB | 12 GB | 360 GB/s | no | – | does not fit |
| RTX 4060 Ti 16 GB | 16 GB | 288 GB/s | no | – | does not fit |
| RTX 4070 12 GB | 12 GB | 504 GB/s | no | – | does not fit |
| RTX 3090 24 GB | 24 GB | 936 GB/s | no | – | does not fit |
| RTX 4090 24 GB | 24 GB | 1,008 GB/s | no | – | does not fit |
| RTX 5090 32 GB | 32 GB | 1,792 GB/s | no | – | does not fit |
| RTX 6000 Ada 48 GB | 48 GB | 960 GB/s | no | – | does not fit |
| L40S 48 GB | 48 GB | 864 GB/s | no | – | does not fit |
| RTX PRO 6000 Blackwell 96 GB | 96 GB | 1,792 GB/s | yes | 424 | faster than you can read |
| A100 80 GB | 80 GB | 2,039 GB/s | tight | 483 | faster than you can read |
| H100 SXM 80 GB | 80 GB | 3,352 GB/s | tight | 793 | faster than you can read |
Single-stream decode ceiling from memory bandwidth at 70% efficiency. Prompt processing and batching not included. See the speed estimator for other quantisations and Apple hardware, or every card compared if you are choosing hardware rather than a model.
Notes
- Ships in MXFP4; OpenAI states it runs on a single 80 GB GPU. Choose the 4-bit row.
- Architecture values from openai/gpt-oss-120b model card. Verify against the model card before buying hardware for this model.
- Estimates assume a single conversation on a card that is otherwise free. A desktop on the same GPU takes 0.5 to 2 GB.
Questions
Can I run gpt-oss 120B on a 24 GB card?
Not comfortably. At Q4_K_M and 8k context it needs about 71.7 GB. The smallest tier that fits is 80 GB.
How much VRAM does gpt-oss 120B need at Q8?
About 130.1 GB at 8k context, or 131.9 GB at 32k. Q8 is near-lossless; use it when it fits.
How fast is gpt-oss 120B on an RTX 4090?
It does not fit a 4090 at Q4 and 8k context, so speed would collapse to CPU offloading. Use a larger card or a smaller quantisation.
See how it compares in which models fit on 8 to 96 GB, or run it without buying the card: Nodegrove attaches a 24, 48 or 96 GB GPU to a workspace that stays saved.