gpt-oss 120B
OpenAI's largest open-weight model. It needs about 65 GB to load, but with few active parameters it is surprisingly quick once loaded, which makes it a favorite on big-memory Macs.
ollama run gpt-oss:120bNeeds about 67 GB of graphics memory, or unified memory on a Mac. First time? Install Ollama, then paste that into a terminal.
Download65 GB
Memory to runAbout 67 GB
Read per token2.9 GB (mixture of experts)
LicenseApache 2.0
Context128K tokens
ReleasedAugust 2025
Good for
- The strongest reasoning you can run at home
- Agents and tool calling
- Big-memory Macs and multi-GPU rigs
Not the best pick for
- Anything under 64 GB of memory
- Image input: it is text only
13 GPUs and Macs
What runs gpt-oss 120B
Estimated speed on each card at the smallest memory size that fits it, from memory bandwidth. As a mixture-of-experts model it reads only part of its weights per token, so it runs much faster than its size suggests.
Runs great 13 cards
- H200141 GB · ~580 tok/s
- H10080 GB · ~400 tok/s
- RTX Pro 6000 Blackwell96 GB · ~220 tok/s
- A10080 GB · ~190 tok/s
- Apple M3 Ultra96 GB · ~99 tok/s
- Apple M1 Ultra128 GB · ~97 tok/s
- Apple M2 Ultra128 GB · ~97 tok/s
- Apple M4 Max128 GB · ~66 tok/s
- Apple M5 Max128 GB · ~56 tok/s
- Apple M2 Max96 GB · ~48 tok/s
- Apple M3 Max96 GB · ~48 tok/s
- NVIDIA DGX Spark128 GB · ~33 tok/s
- Ryzen AI Max+ 395 (Radeon 8060S)96 GB · ~31 tok/s
Cheapest build from our list that runs it well: Ryzen AI Max+ 395 mini PC, 128 GB, from $3,400 used, at about 31 tok/s. See the builds.
Learn
Read more about gpt-oss 120B
- CPU offloading explained: running a model bigger than your VRAMWhat happens when a model doesn't fit in GPU memory, how partial offload works in Ollama and llama.cpp, how slow it gets, and when it's worth it.
- How much RAM do you need for local AI? (System RAM, not VRAM)How much system memory a local AI machine needs when the model is on the GPU, when it spills onto the CPU, on a Mac, and with no GPU at all.
- How to read a model card: what matters for running it locallyParameters, active parameters, context, license, quant files and benchmarks. Which parts of a model card tell you if it will run on your hardware.
- Is running AI locally worth it? Local vs ChatGPT, honestlyWhat you gain and give up by running open models on your own hardware instead of paying for a cloud AI: privacy, cost, quality, and speed.
- Llama 3.3 70B hardware guide: what you need to run it locallyLlama 3.3 70B needs about 45 GB at 4-bit. The setups that run it, two 3090s, a 48 GB card or a big Mac, with estimated speeds and used prices.
- Local AI agents: tool calling, MCP and what works on small modelsHow agents and tool calling work with local models in Ollama, what MCP adds, which models handle tools reliably, and how to keep small models on track.
- Mini PCs and AMD Strix Halo for local AI: unified memory on x86Can a mini PC run local LLMs? What ordinary mini PCs manage, why AMD's Strix Halo chips with up to 128 GB of shared memory are different, and the trade-offs.
- Mixture of experts explained: why a 30B model can run like a 3BWhat MoE models are, what "active parameters" means, and why models like Qwen3 30B-A3B and gpt-oss are so fast on home hardware.
- Running gpt-oss 120B on a Mac: how much memory and how fastgpt-oss 120B needs about 67 GB for the GPU, so a 96 or 128 GB Mac. Which chips run it well, estimated speeds, and how to set it up.
- Running LLMs on a Mac: which M-series chip and how much memoryWhy Macs with Apple silicon are good at local AI, how much unified memory you need for each model size, and how they compare to a PC with a GPU.
- The best local LLM for 32 GB, 48 GB and more (multi-GPU included)What to run with 32 GB, 48 GB or 64 GB+ of GPU memory, from an RTX 5090 to two 3090s to a server full of P100s. Picks, estimated speeds and our rack data.
- The best local LLM for a Mac with 64 GB, 96 GB or 128 GB+What to run on a Mac Studio or MacBook Pro with 64 GB or more of unified memory, from Qwen3 30B-A3B to Llama 3.3 70B and gpt-oss 120B, with estimated speeds.
- The best local LLM for coding, by how much memory you haveWhich open models are worth using for code on 8, 12, 16, 24 GB and up, what they're good and bad at, and how to wire them into your editor.
- The best local LLM for reasoning and mathWhich open models reason best through math, logic and multi-step problems on 8 GB to 64 GB+, how thinking mode works, and why speed matters more than you'd expect.
- The best local model for agents and tool callingWhich open models call tools reliably on 12 GB to 64 GB+, how tool calling works with Ollama, and what to expect from local agents compared with cloud models.
- Thinking models explained: reasoning mode, /think and effort levelsWhat reasoning mode does, when it's worth the wait, how to turn it on and off in Qwen3 and gpt-oss, and what it costs in speed and context.
Compare
Other models
- Qwen3 4BAbout 4 GB · Quick everyday chat and summaries
- Qwen3 8BAbout 7 GB · A solid all-rounder for chat and writing
- Gemma 3 12BAbout 10 GB · Reads images as well as text
- Qwen3 14BAbout 11 GB · Noticeably smarter at reasoning and code
- gpt-oss 20BAbout 16 GB · OpenAI's open model. Fast, strong reasoning
- Gemma 3 27BAbout 19 GB · Google's best open model for its size
- Qwen3 30B-A3BAbout 21 GB · 30B smarts at small-model speed
- Qwen3 32BAbout 22 GB · Strong coding and long answers
- Llama 3.3 70BAbout 45 GB · Close to the big cloud models
- Qwen3 235B-A22BAbout 144 GB · Alibaba's flagship open model, for multi-GPU rigs
- DeepSeek R1 671BAbout 406 GB · The full DeepSeek R1, for the biggest rigs