localLLMrig
Menu

Can I run Qwen3 32B locally?

Qwen3 32B needs about 23 GB of graphics memory. It runs on 6 of the 9 graphics card setups on this page, such as the RTX 3090.

The cheapest graphics card on our list that runs it (it still needs the rest of a PC): GeForce RTX 3090 24GB, $1,370€1,224, used (median of sold listings).

Fast~25 words/sAnswers appear faster than you can read them.

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

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 Studio M4 Max 36GB, $2,116€1,890. price unverified Comfortable~6.7 words/s

Find hardware for Qwen3 32BAbout this model

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 well6

The whole model fits in the graphics memory.

Doesn't fit3

Not enough graphics memory: it needs about 22.7 GB. In a PC with enough normal memory it runs slowly: Budget PC with RTX 3060 12GB, $1,305€1,357. price unverified Very slow~1.4 words/s

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 Qwen3 32B

32.76B parameters. Parameter count is an estimate. More parameters usually means a smarter model that needs more memory.

Licence:
Apache-2.0 source
Longest conversation:
about 61 pages of text (40,960 tokens)
Input:
text
Technical notes

Alibaba's dense 32B model with a thinking mode you can switch on and off, built for code, reasoning and many languages. At our default quality it needs about 22.7 GB, so a 24 GB graphics card holds it, but only just.

Parameter source · Architecture source · Model page

Memory at each quality level

Each download of Qwen3 32B 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 Qwen3 32B
Quality (file)File sizeConversationWorking spaceTotalCheapest machine that holds it
Q8_034.82 GBmeasured GGUF2.1 GB0.8 GB37.8 GBMac mini M4 Pro 64GB, $2,116€1,890 price unverified
Q6_K26.88 GBmeasured GGUF2.1 GB0.8 GB29.8 GBMac mini M4 Pro 64GB, $2,116€1,890 price unverified
Q5_K_M23.21 GBmeasured GGUF2.1 GB0.8 GB26.2 GBMac mini M4 Pro 64GB, $2,116€1,890 price unverified
Q4_K_M19.76 GBmeasured GGUF2.1 GB0.8 GB22.7 GBGeForce RTX 3090 24GB, $1,370€1,224, used (median of sold listings)
IQ4_XS17.71 GBmeasured GGUF2.1 GB0.8 GB20.7 GBGeForce RTX 3090 24GB, $1,370€1,224, used (median of sold listings)
Q3_K_M15.97 GBmeasured GGUF2.1 GB0.8 GB18.9 GBGeForce RTX 3090 24GB, $1,370€1,224, used (median of sold listings)
UD-IQ3_XXS12.97 GBmeasured GGUF2.1 GB0.8 GB15.9 GBGeForce RTX 3090 24GB, $1,370€1,224, used (median of sold listings)
UD-IQ2_XXS9.28 GBmeasured GGUF2.1 GB0.8 GB12.2 GBRadeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list)

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