Can I run Llama 3.3 70B on an RX 9060 XT 16GB?
Key facts
No: it needs about 46 GB and this card has 16 GB of graphics memory.
It needs about 46.0 GB at standard quality (estimate). Checked . Q4 file.
Updated · Llama 3.3 70B on every card
How much memory it needs
That is about 3.0 times what this card has free.
Get a 1-line alert when a faster quant for Llama 3.3 70B drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new open-weight model fits 48 GB VRAM (46.0 GB at Q4 for Llama 3.3 70B) or when used RTX 3090 / 4090 & Mac Studio prices drop >10% — weekly, zero spam.
What runs Llama 3.3 70B instead
The cheapest machine on our list that runs it at least as fast as you read:
Dual RTX 3090, 64 GB RAMabout $3,808€3,592
Comfortable~17.7 tok/sAbout as fast as you read. Fine for chat.Price details
$3,808€3,592
How we priced this
- Graphics cards (2×)$2,790€2,492
- Memory, 64 GB DDR4 (estimate)$555€600
- Rest of the PC: processor, board, case, power supply, storage (estimate)$463€500
The card is the GeForce RTX 3090 24GB. Used price, the typical price of second-hand cards that actually sold. Source: pcprice.watch, checked 24 Oct 2026.
The total is our estimate from these parts, not the price of a ready-made PC in a shop.
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.
A cheaper machine runs it too, but slower than you read:
Mac mini M4 Pro 64GBabout $2,116€1,890
Very slow~2.9 tok/sToo slow for chat. Only for jobs that can wait.Price details
$2,116€1,890
How we priced this
Not checked against a shop listing (price unverified). Price from 16 Oct 2026.
Used-market euro amount from an earlier check of ours. Used prices cannot be checked on the Apple Store.
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.
See our picks for Llama 3.3 70B in Find hardware. Add your budget to see cheaper machines.
For comparison, an RX 9060 XT 16GB costs $522€564, new (cheapest in-stock board on GPU PRIX's German board list). Card details
Llama 3.3 70B on other graphics cards
Runs well2
The whole model fits in the graphics memory.
Doesn't fit8
Not enough graphics memory: it needs about 46.0 GB.
- RTX 3060 12GBhas 12 GB
- RTX 4060 Ti 16GBhas 16 GB
- RTX 3090has 24 GB
- RTX 4090has 24 GB
- RTX 5080has 16 GB
- RX 9060 XT 16GBhas 16 GB
- RTX 5090has 32 GB
- RX 7900 XTXhas 24 GB
More about the model itself, what it is good at and its licence: Llama 3.3 70B.
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 | Doesn't fit | — | 42.5 GBmeasured file | 2.7 GB | 0.8 GB | 46.0 GB | 15.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Doesn't fit | — | 50.1 GB | 2.7 GB | 0.8 GB | 53.6 GB | 15.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Doesn't fit | — | 75.5 GB | 2.7 GB | 0.8 GB | 79.0 GB | 15.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Doesn't fit | — | 141.2 GB | 2.7 GB | 0.8 GB | 144.7 GB | 15.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Doesn't fit | — | 42.5 GBmeasured file | 10.7 GB | 0.8 GB | 54.1 GB | 15.4 GB |
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . Q4 file.
Standard quality (Q4) is the Q4_K_M download. Our estimate at 0.60 bytes per parameter is about 42 GB of weights. A bartowski Llama-3.3-70B-Instruct Q4_K_M file is 42.52 GB (42,520,398,816 bytes). A single 24 GB or 32 GB card is not enough.
Questions
- Can I run Llama 3.3 70B on an RX 9060 XT 16GB?
- No: it needs about 46 GB and this card has 16 GB of graphics memory.
- How much memory does Llama 3.3 70B need?
- About 46.0 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 42.5 GB for the model file (measured), 2.7 GB to hold the conversation and 0.8 GB of working space.
- How fast is Llama 3.3 70B on an RX 9060 XT 16GB?
- There is no speed to give: it doesn't fit on this card.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate