gpt-oss 120B VRAM and RAM requirements
Large open-weight reasoning model with about 117B total parameters. All expert weights must fit, even though only some activate per token.
Uses rounded Ollama MXFP4 download sizes. Requires a runtime and GPU backend that keep expert weights compressed; dequantization can need substantially more memory. KV cache is conservatively allocated at full context for every layer, without sliding-window savings.
This OpenAI model has approximately 116.8 billion parameters. The estimates below use 8,192 context tokens, one conversation, FP16 KV cache and all model weights on the GPU.
| Precision | GPU VRAM target | System RAM target | Estimated weight size |
|---|---|---|---|
| MXFP4 | 74.6 GiB | 72 GiB | 65.00 GB |
How much context can I use?
This calculator supports up to 131,072 tokens for this model. Longer prompts and generated responses share that budget. KV cache grows with context length; additional conversations need additional cache memory.
Can I run gpt-oss 120B in Ollama, LM Studio or vLLM?
The MXFP4 estimate assumes a compatible Ollama, LM Studio or vLLM backend that keeps expert weights compressed. A backend that expands these weights can require much more memory. Check the runtime version, model format and hardware support before downloading. A memory fit alone does not guarantee compatibility or speed.
What do these estimates include?
Weights use rounded published Ollama MXFP4 download sizes, including all experts. They are not calculated from active parameters. We add FP16 attention cache, at least 1 GiB runtime allowance and 10% GPU headroom. System RAM includes an 8 GiB loading allowance. CPU offload, image processing and multi-GPU setups are not modelled.
Official model architecture configuration