Can I run gpt-oss-20b locally?
gpt-oss-20b needs about 13 GB of graphics memory. It runs on 8 of the 9 graphics card setups on this page, such as the RTX 4060 Ti 16GB.
The cheapest graphics card on our list that runs it (it still needs the rest of a PC): Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list).
EU shops · In the US? Switch the currency to USD.
US shops · In Europe? Switch the currency to EUR.
The cheapest complete machine that runs it: Mac mini M6 32GB, $1,416€1,530. price unverified
We don't give a speed for this model yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Which graphics cards run it
Seven popular graphics cards and two PCs with two cards each, at the standard quality (Q4). Click one for the full answer: memory, speed and price.
Runs well8
The whole model fits in the graphics memory.
Doesn't fit1
Not enough graphics memory: it needs about 13.1 GB. In a PC with enough normal memory it runs slowly: Budget PC with RTX 3060 12GB, $1,305€1,357. price unverified
- RTX 3060 12GBhas 12 GB
Cheapest hardware for each size
From all 36 graphics cards, PCs and Macs on our list. "Runs slowly" means part of the model runs from normal memory: cheaper, but much slower. A smaller download needs less memory and answers a little less well.
- Standard quality (MXFP4)Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list)
- Standard quality (MXFP4), runs slowlyBudget PC with RTX 3060 12GB, $1,305€1,357 price unverified
Prices excl. shipping. Euro prices incl. VAT. Dollar prices are converted from our euro prices without EU VAT, before US sales tax.
Prices moved: see Building a local LLM rig in the RAMageddon.
About gpt-oss-20b
21B total, 3.6B active. Parameter count is an estimate. More parameters usually means a smarter model that needs more memory.
- Licence:
- Apache-2.0 source
- Longest conversation:
- about 197 pages of text (131,072 tokens)
- Input:
- text
Technical notes
OpenAI's smaller open model for chat, code and tool use. It ships in 4-bit, so the official file is about 12 GB and fits a 16 GB graphics card. Even the full-quality file is only 13.8 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.
Memory at each quality level
Each download of gpt-oss-20b is a different size. The total adds the file, the memory a conversation of about 12 pages of text (8,192 tokens) takes, and 0.8 GB of working space. A measured file size is labelled; the rest is our estimate. The last column is the cheapest machine that holds the total.
Swipe the table sideways to see every column, up to the cheapest machine.
| Quality (file) | File size | Conversation | Working space | Total | Cheapest machine that holds it |
|---|---|---|---|---|---|
| F16 | 13.79 GBmeasured GGUF | 0.2 GB | 0.8 GB | 14.8 GB | Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list) |
| MXFP4 | 12.11 GBmeasured GGUF | 0.2 GB | 0.8 GB | 13.1 GB | Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list) |
speed: not estimated for MoE yet.
Waiting for prices to drop?
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate