gpt-oss-120b: how much memory, and what runs it
gpt-oss-120b is a large AI model you can download and run on your own computer. It is a mixture of experts: all of it has to fit in memory, but it uses only a small part for each word. It needs about 64 GB of memory at standard quality.
Memory needed
About 64 GB
At standard quality, with room for a conversation of about 12 pages.
Machines that run gpt-oss-120b
Each of these holds the whole model in memory. We do not estimate a speed for this kind of model (a mixture of experts), so these are simply the cheapest.
EU shops · In the US? Switch the currency to USD.US shops · In Europe? Switch the currency to EUR.
Mac Studio M4 Max 128GB
128 GB shared memory · second-hand
$3,683€3,290usedunverified
Machine details →Mac Studio M5 Max 128GB
128 GB shared memory
$5,551€6,000estimate
Machine details →Mac Studio M5 Ultra 96GB
96 GB shared memory
$6,152€6,649new
Machine details →Mac Studio M5 Ultra 256GB
256 GB shared memory
$11,565€12,500estimate
Machine details →
Where our price is for a used card or Mac, these shops mostly sell new ones, so their price can be higher.
About these prices
Each price is the amount we last wrote down for that machine, with its date on the machine page. "Estimate" is our own figure: for a complete PC we add our estimate for the other parts to the graphics card price, and some Mac prices are estimates, not a checked shop listing. "Used" is a second-hand price. "Unverified" means we have no checked shop listing for that exact amount. The shop buttons open a search for that machine at each shop, so you see today's price there. Prices excl. shipping. Euro prices incl. VAT. Dollar prices are converted from our euro prices without EU VAT, before US sales tax.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate
Memory at each quality level
A lower quality level makes the model smaller, so it fits on a smaller machine. Standard (Q4) is what most people run.
| Quality | Memory needed |
|---|---|
| Q4 · standard (smallest that keeps quality) | 64.5 GB |
| Q5 · a bit sharper, a bit bigger | 66.5 GB |
| Q8 · near full quality, almost twice Q4 | 66.5 GB |
| FP16 · full quality, over three times Q4 | 66.5 GB |
With a conversation of 8,192 tokens · about 12 pages of text.
How we worked this out
At standard quality: 63.4 GB for the model itself (a measured file), 0.3 GB for a conversation of 8,192 tokens, and 0.8 GB for the software.
Size source: huggingface.co/openai/gpt-oss-120b. 117B parameters in total, 5.1B used for each word. The memory counts the total.
OpenAI's larger open model for reasoning, code and tool use. It ships in 4-bit, so the official file is about 63 GB: no single graphics card on our list holds it, but a 96 GB or 128 GB Mac or a 128 GB mini PC does. Even the full-quality file is only 65.4 GB, so our higher quality levels use that file's size. Lower-quality versions we checked keep that 4-bit core and save under 1 GB.
Licence
Commercial use: yes
Commercial use allowed. Keep the licence and copyright notice when you share the weights.
Licence: Apache-2.0 · checked 21 Oct 2026
Our reading of the licence, not legal advice.
Will gpt-oss-120b run on my graphics card?
Common questions
- How much memory does gpt-oss-120b need?
- About 64.5 GB at standard quality (Q4) with a conversation of 8,192 tokens: 63.4 GB for the model itself, 0.3 GB for the conversation and 0.8 GB for the software. The model size is a measured file; the conversation and software parts are our estimate.
- Does gpt-oss-120b fit on a single 24 GB graphics card?
- Not in full. It needs about 64.5 GB, and a 24 GB card leaves about 23.4 GB usable.
- Are the speeds measured?
- We do not show a speed for this model. It is a mixture-of-experts model, and our estimate would not be reliable for that design.