Text / OpenAI
gpt-oss · 120B
An open-weight reasoning and tool-use model packaged by Ollama at 65 GB for high-memory local systems or rented GPUs.
Verified sourceSource checked 9/23/2026
LOCALRENTED GPUOPEN WEIGHTS
At a glance
- Parameters
- 120B total
- Architecture
- Mixture of experts, MXFP4
- Context length
- 131,072
- License
- Apache 2.0
- Disk space
- 65 GB
- Software
- Ollama
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Private, high-capacity reasoning on an 80 GB-class GPU or large unified-memory machine.
- Structured output and local tool-use experiments.
Tradeoffs
- A 65 GB download needs substantial extra runtime and context memory.
- Published package fit is not a measured responsiveness result for your hardware.
Ways to run it
Ollama · Windows, macOS, Linux
Ollama lists a 65 GB package and says the large variant fits on a single 80 GB GPU. Usable context and speed still depend on the machine.
ollama run gpt-oss:120bExplore its uses
REASONINGTOOL CALLINGAGENTS
Keep exploring
Text
Prism MLBonsai 2 · 27B
A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.
MODEL SIZE27.36B
Text
DeepSeekDeepSeek V4.1 Flash
A multimodal reasoning model with a compressed key-value cache, published as open weights.
Text
QwenQwen3.8-Flash-Next
An experimental open-weight multimodal model with sparse attention and 262K native context.
MODEL SIZE125B language · 6B active