llama4-scout-17b
Architecture mixture of experts48 LayersLicense llama4Maximum context 10,240kVocabulary 202,048
At Q4_K_M it is a 60.87 GiB file, and it fits on 5 of the 18 machines we measure (the one with the least memory: Xiaomi AI Cube, 80 GB — engineering prototype). Watch the context, though: at its maximum of 10240k tokens it takes 481.12 GiB, more than the file itself — and the same content in German takes ×1.30 the tokens of English.
Model size at Q4_K_M
Measured by Local AI Scope
Context memory at 8k tokens
Measured by Local AI Scope
What German costs versus English
Measured by Local AI Scope
Sizes of the real published files
These are the sizes of the files actually published by the author, added up when the model ships split into parts. Not an estimate from the parameter count.
| Compression | Model size |
|---|---|
Q8_0 |
106.67 GiB |
Q6_K |
82.36 GiB |
Q5_K_M |
71.29 GiB |
Q5_K_S |
69.16 GiB |
Q4_K_M |
60.87 GiB |
Q4_K_S |
57.23 GiB |
IQ4_XS |
53.69 GiB |
Q3_K_M |
48.20 GiB |
This model also reads images. For that it needs a second file, the vision projector (mmproj-F16.gguf, 1.63 GiB), published next to the model and not included in the figures on this page: they count text only. If you are going to send it images, add it to the model size.
Context memory
Computed from the attention pattern this model declares layer by layer, not from the generic formula. That is why the figure is often far smaller than other calculators tell you.
- 8k tokens → 1.50 GiB
- 32k tokens → 2.62 GiB
- 128k tokens → 7.12 GiB
What it costs in each language
Measured by running this model’s own tokenizer over the same content in four languages. Tokens are what you pay for in context, in memory and in your cloud bill.
| Kind of text | EN | ES | FR | DE |
|---|---|---|---|---|
| Code | — | ×1.19 | ×1.32 | ×1.40 |
| Contracts | — | ×1.13 | ×1.23 | ×1.26 |
| Business email | — | ×1.13 | ×1.21 | ×1.23 |
| Support tickets | — | ×1.21 | ×1.37 | ×1.26 |
English is the baseline: every figure is how many times more tokens the same content costs in that language. Average across the whole corpus: DE ×1.30.
Where it fits
Fits means the model, its context memory and the working headroom all fit at the stated context, leaving the system its share. 5 of the 18 machine profiles tested (Q4_K_M, 8k tokens).
If you are willing to compress it more, it does run where the table says no: at Q4_K_S (57.23 GiB), up to 16k tokens of context, on Mac with M4 Max and 64 GB · Mac mini with M5 Pro and 64 GB. Below Q4_K_M the model loses a little quality, and at Q3_K_M you can tell; that is why the table above sticks to Q4_K_M.