Llama-3.2-11B-Vision-Instruct
Meta · meta-llama/Llama-3.2-11B-Vision-Instruct
Weights license: Publisher terms: Llama 3.2 · code and components may use other terms
Quality
Quality · LMArena · vision
LMArena 2026-10-19 · human-preference rating · higher is better · this model outlined
- Color = publisher
Source: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0 · models without a rating are not drawn (no rating ≠ 0)
993 ± 11 · LMArena · vision · Confidence interval 981–1,004 · 4,817 votes
Reported by the publisher
- MMMU (val, CoT)
- 50.7Image · College-level Problems and Mathematical Reasoning
- MMMU-Pro, Standard (10 opts, test)
- 33.0Image · College-level Problems and Mathematical Reasoning
- MMMU-Pro, Vision (test)
- 23.7Image · College-level Problems and Mathematical Reasoning
- MathVista (testmini)
- 51.5Image · College-level Problems and Mathematical Reasoning
- ChartQA (test, CoT)
- 83.4Image · Charts and Diagram Understanding
- AI2 Diagram (test)
- 91.1Image · Charts and Diagram Understanding
- DocVQA (test)
- 88.4Image · Charts and Diagram Understanding
- VQAv2 (test)
- 75.2Image · General Visual Question Answering
Every reported result
Values as printed on the card, with the publisher's own settings (card section: Benchmarks - Image Reasoning › Instruction Tuned Models); column “Llama 3.2 11B”. 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.
Meta released Llama-3.2-11B-Vision-Instruct on 2024-09-25: a vision-language model that answers about images, with 10.7B parameters on the Hugging Face count and the Publisher terms: Llama 3.2 license. Languages the publisher declares: en, de, fr, it, pt, hi, es, th.
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 8 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 90
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 90
Within memory, outside the fast part 26
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.
Show all 26
One memory tier short 3
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)
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- meta-llama/Llama-3.2-11B-Vision-Instruct
- Task
- image-text-to-text
- Architecture
- MllamaForConditionalGeneration
- Library in source
- transformers
- Weight license
- Publisher terms: Llama 3.2Llama 3.2 MODEL_CARD_VISION.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 3.2 Community License (meta-llama/llama-models) · read 2026-10-18license text
- Languages
- en, de, fr, it, pt, hi, es, thModel card metadata · read 2026-10-25source
- Released
- Llama 3.2 Vision MODEL_CARD_VISION.md, 'Model Release Date: Sept 25, 2024' (meta-llama/llama-models, GitHub) · read 2026-10-18source
Every stored field
- Revision checked
- 9eb2daaa8597bf192a8b0e73f848f3a102794df5
- Architecture
- MllamaForConditionalGeneration
- Library
- transformers
- Hub task tag
- image-text-to-text
- Formats
- transformers, safetensors, pytorch
- Access
- Gated (manual)
- Publisher kind
- Official
- Repository created
- 2024-09-18creation is not the model's release
- Repository updated
- 2024-12-04a commit is not a release date
- Hub downloads (30 days) · likes
- 57,014 · 1,679this repository only · read 2026-10-25
- 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.
- Publisher model card
- License: Llama 3.2 MODEL_CARD_VISION.md (meta-llama/llama-models, GitHub)
- Release date: Llama 3.2 Vision MODEL_CARD_VISION.md, 'Model Release Date: Sept 25, 2024' (meta-llama/llama-models, GitHub)
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.






























































