Skip to content
Local AI Wizard
Your machine
Theme

Llama-4-Scout-17B-16E-Instruct

Meta · meta-llama/Llama-4-Scout-17B-16E-Instruct

Weights license: Publisher terms: Llama 4 · code and components may use other terms

LMArena · vision1,128 ± 10#13 of 22 rated here · 2026-10-19
Memory needed~82 GBQ4 weights + working room, before the machine's reserve
Parameters108.6 BHub safetensors total
Repository updated2025-05-22A commit is not a release date

Quality

Reported by the publisher

9 results · Meta's model card · read 2026-10-25
MMMU
69.4Image Reasoning
MMMU Pro^
52.2Image Reasoning
MathVista
70.7Image Reasoning
ChartQA
88.8Image Understanding
DocVQA (test)
94.4Image Understanding
LiveCodeBench (10/01/2024-02/01/2025)
32.8Coding
MMLU Pro
74.3Reasoning & Knowledge
GPQA Diamond
57.2Reasoning & Knowledge
Every reported result9
MGSM
90.6Multilingual

Values as printed on the card, with the publisher's own settings (card section: Benchmarks › Instruction tuned models); column “Llama 4 Scout”. Not comparable across publishers and not used in any ranking. Model card

Quality × memory

No comparable quality × memory pair

This entry has no score on a benchmark that is drawn against planning memory.

Consider it for

Meta released Llama-4-Scout-17B-16E-Instruct on 2025-04-05: a vision-language model that answers about images, with 108.6B parameters on the Hugging Face count and the Publisher terms: Llama 4 license. Languages the publisher declares: ar, de, en, es, fr, hi, id, it, pt, th, tl, vi.

Check first

License: commercial use allowed with conditions: Over 700M monthly users needs a Meta license; show "Built with Llama"; multimodal versions are not licensed to people or companies based in the EU (Acceptable Use Policy). At Q4 the weights load about 81.5 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick. Downloading requires accepting the publisher's terms on Hugging Face.

Runs on

Fast memory holds it 14

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 14

Within memory, outside the fast part 1

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

One memory tier short 2

The same machines with the next memory size up would hold it in fast memory.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

The model card could not be read (missing or gated)

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
image-text-to-text
Architecture
Llama4ForConditionalGeneration
Library in source
transformers
Weight license
Publisher terms: Llama 4Llama 4 MODEL_CARD.md (meta-llama/llama-models, GitHub) · read 2026-10-18source
Commercial use
Allowed with conditions Over 700M monthly users needs a Meta license; show "Built with Llama"; multimodal versions are not licensed to people or companies based in the EU (Acceptable Use Policy) · Llama 4 Community License (meta-llama/llama-models) · read 2026-10-18license text
Languages
ar, de, en, es, fr, hi, id, it, pt, th, tl, viModel card metadata · read 2026-10-25source
Released
Llama 4 MODEL_CARD.md, 'Model Release Date: April 5, 2025' (meta-llama/llama-models, GitHub) · read 2026-10-18source
Every stored field13 fields
Revision checked
92f3b1597a195b523d8d9e5700e57e4fbb8f20d3
Architecture
Llama4ForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Declared base models
meta-llama/Llama-4-Scout-17B-16E
Formats
transformers, safetensors, pytorch
Access
Gated (manual)
Publisher kind
Official
Repository created
2025-04-02creation is not the model's release
Repository updated
2025-05-22a commit is not a release date
Hub downloads (30 days) · likes
133,972 · 1,379this repository only · read 2026-10-25
Read from the Hub page
transformers class, task tagsHub overview and file listing · read 2026-10-18
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.