Can I run gpt-oss-20b on an RX 9060 XT 16GB?
Key facts
Yes. gpt-oss-20b runs on an RX 9060 XT 16GB, about 103 tokens per second (tok/s).
It needs about 13.1 GB at standard quality (estimate). Checked . ggml-org MXFP4 GGUF (official ggml-org repo; the model's native 4-bit, not Q4_K_M).
The cheapest graphics card on our list that holds it at Q4 is the Radeon RX 9060 XT 16GB. On an RX 9060 XT 16GB, at 32,768 tokens of context, it still fits in graphics memory (estimate).
Updated · gpt-oss-20b on every card
How much memory it needs
It uses about 85% of the memory that is free on this card.
Get a 1-line alert when a faster quant for gpt-oss-20b drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new open-weight model fits 16 GB VRAM (13.1 GB at Q4 for gpt-oss-20b) or when used RTX 3090 / 4090 & Mac Studio prices drop >10% — weekly, zero spam.
What an RX 9060 XT 16GB costs
Radeon RX 9060 XT 16GB$522€564new (cheapest in-stock board on GPU PRIX's German board list)
EU shops · Shown to visitors in Europe.US shops · Shown to visitors outside Europe.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
Price details
$522€564
How we priced this
New (cheapest in-stock board on GPU PRIX's German board list).
Source: GPU PRIX, checked 17 Oct 2026.
An ASUS Prime at €563.90. A lower Amazon.de offer, an XFX Swift at €474.78, was also listed as in stock, but not on that board list; we did not use it.
Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.
It is also the cheapest graphics card on our list that runs this model.
The cheapest complete machine that runs it: Mac mini M6 32GB, about $1,416€1,530. Fast~36 tok/s
If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work
As an Amazon Associate I earn from qualifying purchases.
Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.
Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.
gpt-oss-20b on other graphics cards
Runs well9
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 | Speed | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Runs | Fast~103 tok/s | 12.1 GBmeasured file | 0.2 GB | 0.8 GB | 13.1 GB | 15.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Runs | Fast~92 tok/s | 13.8 GB | 0.2 GB | 0.8 GB | 14.8 GB | 15.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Runs | Fast~92 tok/s | 13.8 GB | 0.2 GB | 0.8 GB | 14.8 GB | 15.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Runs | Fast~92 tok/s | 13.8 GBmeasured file | 0.2 GB | 0.8 GB | 14.8 GB | 15.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Runs | Fast~82 tok/s | 12.1 GBmeasured file | 0.8 GB | 0.8 GB | 13.7 GB | 15.4 GB |
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . ggml-org MXFP4 GGUF (official ggml-org repo; the model's native 4-bit, not Q4_K_M).
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. Our speed estimate streams the 3.6B active parameters, not all 21B.
Measured gpt-oss-20b on an RX 9060 XT 16GB yourself? Send us your llama-bench result.
Questions
- Can I run gpt-oss-20b on an RX 9060 XT 16GB?
- Yes. gpt-oss-20b runs on an RX 9060 XT 16GB, about 103 tokens per second (tok/s).
- 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 RX 9060 XT 16GB?
- Fast: about 103 tokens per second (tok/s). Answers appear faster than you can read them. This is our estimate, not a measured test.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate