Qwen

Qwen3-4B-Instruct-2507

A model by Qwen you run on your own computer, offline: how it did in our Arabic test, the size of each of its files as Hugging Face lists it, the memory a conversation takes worked out from the file itself as llama.cpp reserves it, and whether it fits your card and RAM.

Released:

Compare two products

The graphics card in your computer

Press the button and your browser reads the name of your computer's graphics card, which we pick in the check if the Lab has it.

The card's name is never sent to our site: it stays in this browser alone until you press "Forget my device".

How the name is read

Can your PC run it?

In GB, as Windows shows it under Settings > System > About.

Everything in the conversation, your questions and the model's answers. A token is a piece of a word.

Going by this page's figures

Pick the graphics card in your computer or type its RAM, and we'll say which of this model's files fit.

    Worked out from the figures in the table below, not tried on your card: the file and the conversation memory, about 0.7 GB llama.cpp reserves to work in, and 1 GB of the card it leaves free for your screen and programs. Speed is not measured.

    How we work out whether a model fits

    Specifications

    Specifications and their sources
    The model
    Parameters 4 billion[1]
    Longest conversation 262,144 tokens[2]
    Licence apache-2.0[1]
    GGUF files to download
    Q4_K_M file 2.5 GB[2]
    Q5_K_M file 2.89 GB[3]
    Q6_K file 3.31 GB[4]
    Q8_0 file 4.28 GB[5]
    Conversation memory (llama.cpp)
    Conversation memory per 1,000 tokens 147.5 MB[2]
    Conversation memory, fixed part 0 MB[2]
    The Arabic test
    Arabic score 80 %[6] Asked through nscale, one of Hugging Face's providers
    Understanding Arabic text 85 %[6]
    Following Arabic instructions 56 %[6]
    Does not invent 100 %[6]
    Made-up products it gave specs for (of 8) 0[6]
    Answers that slipped into another script (of 56) 1[6]

    Compare two products