Can I run gpt-oss-20b on an RTX 3090?
Yes. gpt-oss-20b runs on an RTX 3090: the whole model fits in its graphics memory.
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.
Updated · gpt-oss-20b on every card
How much memory it needs
It uses about 56% of the memory that is free on this card.
What an RTX 3090 costs
GeForce RTX 3090 24GB$1,370€1,224used (median of sold listings)
EU shops · In the US? Switch the currency to USD.US shops · In Europe? Switch the currency to EUR.
Price details
$1,370€1,224
How we priced this
Used price, the typical price of second-hand cards that actually sold.
Source: pcprice.watch, checked 16 Oct 2026.
New price, the lowest in stock in the EU: $2,052€2,218 at GPU PRIX, 16 Oct 2026. A Zotac Trinity OC from France.
Used median €1,224 (typical €1,136–€1,312) from 232 cards sold on eBay in the past 90 days, recorded 16 Oct 2026. Not an EU shop price.
Prices excl. shipping. Euro prices incl. VAT. Dollar prices are converted from our euro prices without EU VAT, before US sales tax.
The cheapest graphics card on our list that also 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).
The cheapest complete machine that runs it: Mac mini M6 32GB, $1,416€1,530. price unverified
gpt-oss-20b on other graphics cards
Runs well8
The whole model fits in the graphics memory.
Doesn't fit1
Not enough graphics memory: it needs about 13.1 GB.
- RTX 3060 12GBhas 12 GB
More about the model itself, what it is good at and its licence: gpt-oss-20b.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this card.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Runs | 12.1 GBmeasured file | 0.2 GB | 0.8 GB | 13.1 GB | 23.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Runs | 13.8 GB | 0.2 GB | 0.8 GB | 14.8 GB | 23.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Runs | 13.8 GB | 0.2 GB | 0.8 GB | 14.8 GB | 23.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Runs | 13.8 GBmeasured file | 0.2 GB | 0.8 GB | 14.8 GB | 23.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Runs | 12.1 GBmeasured file | 0.8 GB | 0.8 GB | 13.7 GB | 23.4 GB |
speed: not estimated for MoE yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Questions
- Can I run gpt-oss-20b on an RTX 3090?
- Yes. gpt-oss-20b runs on an RTX 3090: the whole model fits in its graphics memory.
- How much memory does gpt-oss-20b need?
- About 13.1 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 12.1 GB for the model file (measured), 0.2 GB to hold the conversation and 0.8 GB of working space.
- How fast is gpt-oss-20b on an RTX 3090?
- 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.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate