Can I run gpt-oss 120B locally?
Not on a single consumer GPU. Even at MXFP4 with 8K context, gpt-oss 120B needs about 62 GB. That takes several GPUs, a workstation card, or a machine with a lot of fast system RAM, where it runs slowly.
Memory needed by compression and context length
| Compression | 4K context | 8K context | 32K context | 128K context |
|---|---|---|---|---|
MXFP4 The format the model is released in. | 62 GB | 62 GB | 63 GB | 66 GB |
Total memory: model weights, context (KV cache) and about 1 GB of runtime overhead. To run entirely on the GPU, VRAM must be about 5% larger than this.
GPUs that run gpt-oss 120B entirely on the GPU
None of the GPUs in our database has the 66 GB of VRAM it needs at MXFP4.
Model facts
- Parameters
- 116.8B (5.1B active, mixture-of-experts)
- Max context
- 128K tokens
- License
- Apache 2.0
- Released
- Aug 2025
Check it with your hardware
Change the compression, context length and system RAM in the calculator.
Open calculator