Can I run Llama 4 Scout locally?

Of the setups on this page, only the 2 two-card PCs run it, and only slowly: Llama 4 Scout needs about 68 GB of graphics memory, so part of it has to run from normal memory. A single card does not have enough graphics memory on its own. In a PC with enough normal memory it also runs slowly on one card.

The cheapest machine on our list that runs it: Mac Studio M4 Max 128GB, $3,683€3,290. price unverified

Our price is for a used Mac. These shops mostly sell new ones, so their price can be higher.

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 slowly2

Part of the model spills into normal memory, which is much slower.

Doesn't fit7

Not enough graphics memory: it needs about 67.8 GB. In a PC with enough normal memory it runs slowly: Mid-range PC with RTX 4060 Ti 16GB, $1,849€1,999. price unverified

Every model on every card

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.

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 Llama 4 Scout

108.64B total, 17B active. Parameter count is an estimate. More parameters usually means a smarter model that needs more memory.

Licence:
Llama 4 Community License source
Longest conversation:
about 15729 pages of text (10,485,760 tokens)
Input:
text + image in, text out
Released:
source
Technical notes

Meta's mixture-of-experts model with image input and a very long context window. At our default quality it needs about 68 GB, so no single graphics card on our list holds it, but a 96 GB or 128 GB Mac or a 128 GB mini PC does. Because it reads images, Meta's licence gives no rights to people or companies based in the EU. End users of a product built on it are not affected.

Parameter source · Architecture source · Model page

Memory at each quality level

Each download of Llama 4 Scout 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.

Memory per quant for Llama 4 Scout
Quality (file)File sizeConversationWorking spaceTotalCheapest machine that holds it
BF16215.56 GBmeasured GGUF1.6 GB0.8 GB218.0 GBNo machine on our list runs this size.
Q8_0114.53 GBmeasured GGUF1.6 GB0.8 GB116.9 GBMac Studio M5 Ultra 256GB, $11,565€12,500 price unverified
Q6_K88.43 GBmeasured GGUF1.6 GB0.8 GB90.8 GBMac Studio M4 Max 128GB, $3,683€3,290 price unverified
Q5_K_M76.55 GBmeasured GGUF1.6 GB0.8 GB79.0 GBMac Studio M4 Max 128GB, $3,683€3,290 price unverified
Q4_K_M65.36 GBmeasured GGUF1.6 GB0.8 GB67.8 GBMac Studio M4 Max 128GB, $3,683€3,290 price unverified
IQ4_XS57.65 GBmeasured GGUF1.6 GB0.8 GB60.1 GBMac Studio M4 Max 128GB, $3,683€3,290 price unverified
Q3_K_M51.76 GBmeasured GGUF1.6 GB0.8 GB54.2 GBMac Studio M4 Max 128GB, $3,683€3,290 price unverified
UD-Q2_K_XL42.38 GBmeasured GGUF1.6 GB0.8 GB44.8 GBMac mini M4 Pro 64GB, $2,116€1,890 price unverified
UD-IQ1_S32.47 GBmeasured GGUF1.6 GB0.8 GB34.9 GBMac mini M4 Pro 64GB, $2,116€1,890 price unverified

speed: not estimated for MoE yet.

Waiting for prices to drop?

Get an email when GPU prices drop. No spam, unsubscribe anytime. Privacy

Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate