hostinglinks.
PRACTICAL TECH, EXPLAINED

Specialist · reviewed 14 October 2026

gpt-oss 120B VRAM and RAM requirements

Run this model with Ollama or LM Studio ↓

Check a model download using its actual file size.

New to local AI? Find your GPU memory and understand these settings.

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.

Estimated memory for gpt-oss 120B
PrecisionGPU VRAM targetSystem RAM targetWeight allowance
MXFP474.6 GiB72 GiB65.00 GB

What changes with a longer conversation?

For gpt-oss 120B, the architecture used here has 36 layers, 8 KV heads and a head dimension of 64. The following comparison keeps MXFP4 weights fixed and changes only context. It uses the same calculation as the main tool.

gpt-oss 120B: context and memory trade-offs
ContextKV cacheGPU targetMac unified target
1,024 tokens0.07 GiB74.1 GiB104 GiB
4,096 tokens0.28 GiB74.3 GiB104 GiB
8,192 tokens0.56 GiB74.6 GiB104 GiB
32,768 tokens2.25 GiB76.5 GiB104 GiB
131,072 tokens9.00 GiB84.0 GiB112 GiB

Start with the shortest context that covers your task. If the GPU target is close to your available capacity, test a short conversation before loading a long document. These values do not measure speed or answer quality. Understand the trade-offs or troubleshoot a loading failure.

How much context can I use?

The reviewed model context limit is 131,072 tokens. The calculator currently offers settings up to 131,072 tokens. 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.

Published MXFP4 download size

Architecture catalogue reviewed 14 October 2026. These are planning estimates, not measured benchmarks. Catalogue coverage and limitations.

Official model architecture configuration

Run gpt-oss 120B locally

These steps use MXFP4 weights. Compare the MXFP4 row above with your available memory before downloading. The command does not choose Q8 or 16-bit weights, even if you explored those in the calculator.

View the exact Ollama download, file size and licence. Download tags checked 16 September 2026; publishers can update their files. File size is not the same as total running memory.

Large download: this model needs substantial storage and memory. Check the published file size and your hardware first; a successful download does not mean it will fit on one GPU.

Option 1: Ollama

  1. Install and start Ollama from its official website. Check its supported GPUs.
  2. Open Terminal on Mac or Linux, or PowerShell on Windows. Run the command below. On first use, Ollama downloads the model before opening a chat.
ollama run gpt-oss:120b

Inside the Ollama chat, enter this setting before your first prompt to use the same 8,192-token context as the table above:

/set parameter num_ctx 8192

Then try a short prompt such as “Explain how a solar panel works in three sentences.” In a second terminal, run ollama ps to inspect whether the model is on the GPU or partly on the CPU. CPU offload changes performance and falls outside this calculator's full-GPU assumptions. See Ollama's context and GPU-loading instructions.

Option 2: LM Studio

  1. Install LM Studio and open its model discovery screen.
  2. Search for gpt-oss 120B. Match the family, size and variant exactly. Check the publisher and model card; community conversions are not necessarily published by the original model creator.
  3. Choose a supported native MXFP4 gpt-oss download and compatible runtime. An expanded or differently quantized version may need substantially more memory.
  4. Load the model into a chat. Set the context length to 8,192 tokens and check the GPU offload settings. Try a short prompt before adding a long conversation or document.

LM Studio's official model download guide. Search results and available formats can change; we have verified the Ollama tags, not every community LM Studio conversion.

If the model will not load

Check your runtime version and GPU support, then close other memory-heavy apps. Try a shorter context or a smaller model and recalculate. Confirm that the downloaded format matches the estimate. Extra conversations, vision processing and runtime-specific allocations can increase memory use.

Find a smaller model for my computer · Check my memory and settings

Compare hardware and change context in the VRAM calculator

Compare other local LLM models · Privacy and cookies