Model Follower.

Up to date

Rebuilt
2026-10-25 06:54 UTC
Release radar
117 on watch
Hub snapshot
2026-10-25
Re-checked
daily · every number sourced and dated

Models › Llama-3.2 family

Llama-3.2-11B-Vision

Hugging Face ↗ Follow changes

meta-llama Llama 3.2 Community License out 2 years ago

10.6B parameters, images and text in, text out.

Verified 2026-10-25 Rank #516 in LLMs · score 75.9 method v1 Sources 3 Downloads 30d 12.2k · #494 of 619 tracked

Can I run it?6.4GB at INT4Estimatefits a 16 GB cardmethod
Can I use it?Llama 3.2 Community LicenseAs 3.1; EU multimodal restriction in the textlicence file2026-10-24
Do people use it?12.2kdownloads, 30 days#494 of 619 we track · below the median+0 likes, downloads +2% this week616 likesHugging Face2026-10-24

Worth reading

Picked by rule from 25 tracked pieces: the lab's own post, the most shared, a field report, the latest.

25 best of 25 tracked

The 2 picks above, plus these 23. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

  1. ArticleLlama 3.2: Revolutionizing edge AI and vision with open, customizable modelsai.meta.com · 2024-09-25 · 924 HN pts · official
  2. ArticleLlama 3.2 released: Multimodal, 1B to 90B sizesllama.com · 2024-09-25 · 89 HN pts · official
  3. ArticleI Self-Hosted Llama 3.2 with Coolify on My Home Servergeek.sg · 2024-10-16 · 221 HN pts
  4. ArticleOllama 0.4 is released with support for Meta's Llama 3.2 Vision models locallyollama.com · 2024-11-06 · 182 HN pts
  5. ArticleLlama can now see and run on your device – welcome Llama 3.2huggingface.co · 2024-09-25 · 26 HN pts
  6. ArticleDownload Llama 3.2 1B, 3B, 11B, 90Bllama.com · 2024-09-25 · official
  7. ArticleShow HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcriptsbilawal.net · 2025-09-01
  8. ArticleShow HN: Llama 3.2 3B and Keiro Research achieves 85% on SimpleQAkeirolabs.cloud · 2026-03-07
  9. ArticleVerbatim AI – on-device transcription (Whisper) + summaries (Llama 3.2)apps.apple.com · 2026-04-21 · 2 HN pts
  10. CodeLlama 3.2 Releasegithub.com · 2024-09-25 · 12 HN pts
  11. ArticleLoad Llama-3.2 WebGPU in the browser from a local foldersimonwillison.net · 2025-09-09 · 3 HN pts
  12. ArticleRWKV-7 beats Llama 3.2 with 3x fewer training tokens and formally exceeds TC^0ai.gopubby.com · 2026-02-23
  13. CodePydanticAI using Ollama (llama3.2) running locallygithub.com · 2024-12-06
  14. CodeShow HN: Recall – open-source local file organizer using Llama 3.2 and Ollamagithub.com · 2025-12-10
  15. CodeImplementing the Llama 3.2 1B and 3B Architectures from Scratchgithub.com · 2024-10-05
  16. CodeShow HN: MLX.zig – Llama 3.2 in Ziggithub.com · 2025-03-14
  17. ArticleOpen Source wireframe to app powered by Llama 3.2 Visionnapkins.dev · 2024-09-25
  18. ArticleShow HN: Finetune Llama 3.2 Vision in a Colabcolab.research.google.com · 2024-11-21
  19. DiscussionLlama 3.2: Lightweight models for edge devicestwitter.com · 2024-09-25
  20. DiscussionLlama 3.2 1B and 3B on-device modelstwitter.com · 2024-09-25
  21. ArticleRun Llama 3.2 3B on your phoneapps.apple.com · 2025-01-18
  22. ArticleLLama3.2-vision as almost perfect OCR?demo.doctractor.com · 2024-11-18
  23. DiscussionI built this robot and gave it a llama3.2 braintwitter.com · 2025-01-14

Where it's used

Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.

No API provider serves it, so its downloads are people running it themselves: 3 quantized builds and 75 Spaces.

  • As a service0no API provider listed
  • On own hardware3quantized builds
  • Built on209 fine-tunes · 11 adapters · 0 merges
  • In apps75Hugging Face Spaces

Top Spaces running it: TIGER-Lab/MEGA-Bench ♥ 51 · Aashi/Text-Image-Analyzer ♥ 18 · guangyangmusic/legato-demo ♥ 8 · sailfish/explain-image ♥ 2

Will it fit?

Weights only, an estimate: leave room for the KV cache. Method

Fits a 16 GB card at INT4

About 6.4 GB at INT4, 13 GB at FP8, 26 GB at BF16: weights only, so leave room for the KV cache.

16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 6.4 GB of weights (estimate; KV cache and activations extra)INT46.4 GBFP8: about 13 GB of weights (estimate; KV cache and activations extra)FP813 GBBF16: about 26 GB of weights (estimate; KV cache and activations extra)BF1626 GB
16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 6.4 GB of weights (estimate; KV cache and activations extra)INT46.4 GBFP8: about 13 GB of weights (estimate; KV cache and activations extra)FP813 GBBF16: about 26 GB of weights (estimate; KV cache and activations extra)BF1626 GB

Estimate params × bytes per param × 1.2 · how we estimate

The story so far

Weights, every dated article, and repo commits on one rail.

10 dated articles and 0 repo commits so far

Teal is the weights (2024-09-18), amber triangles are 10 dated articles (each links to it).

OctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctLlama 3.2: Revolutionizing edge AI and vision with open, customizable models · 2024-09-25Show HN: Llama 3.2 Interpretability with Sparse Autoencoders · 2024-11-21Llama 3.2 released: Multimodal, 1B to 90B sizes · 2024-09-25I Self-Hosted Llama 3.2 with Coolify on My Home Server · 2024-10-16Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy · 2026-06-23Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally · 2024-11-06Llama can now see and run on your device – welcome Llama 3.2 · 2024-09-25Verbatim AI – on-device transcription (Whisper) + summaries (Llama 3.2) · 2026-04-21Llama 3.2 Release · 2024-09-25Load Llama-3.2 WebGPU in the browser from a local folder · 2025-09-09Weights 2024-09-18 · 2024-09-18Weights 2024-09-18now
OctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctLlama 3.2: Revolutionizing edge AI and vision with open, customizable models · 2024-09-25Show HN: Llama 3.2 Interpretability with Sparse Autoencoders · 2024-11-21Llama 3.2 released: Multimodal, 1B to 90B sizes · 2024-09-25I Self-Hosted Llama 3.2 with Coolify on My Home Server · 2024-10-16Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy · 2026-06-23Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally · 2024-11-06Llama can now see and run on your device – welcome Llama 3.2 · 2024-09-25Verbatim AI – on-device transcription (Whisper) + summaries (Llama 3.2) · 2026-04-21Llama 3.2 Release · 2024-09-25Load Llama-3.2 WebGPU in the browser from a local folder · 2025-09-09Weights 2024-09-18 · 2024-09-18Weights 2024-09-18now

What people built on it

23 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

23 derivatives on the Hub, led by 11 adapters

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

3 quantized (Hugging Face model tree)9 fine-tunes (Hugging Face model tree)11 adapters (Hugging Face model tree)3 quantized9 fine-tunes11 adapters
3 quantized (Hugging Face model tree)9 fine-tunes (Hugging Face model tree)11 adapters (Hugging Face model tree)3 quantized9 fine-tunes11 adapters

All variants →

Reference

Everything else, folded: the full tables, every source.

Use-case evidence

1 use case

What it is good at 1 use case

Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.

Facts

17 fields

Listed in LLMs

Facts

Pipeline tagimage-text-to-text
Librarytransformers
ArchitecturesMllamaForConditionalGeneration
Model typemllama
Params by dtypeBF16: 10,642,941,475
Size bandL
MoEno
Gatedmanual
PapersarXiv:2204.05149
LicenseLlama 3.2 Community License (llama3.2)
Hub snapshot2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: not in registry · MllamaForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · MllamaForConditionalGeneration · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed

vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for Llama-3.2-11B-Vision: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)26 GB · Single high-end GPU (<80 GB)
FP8 (1 byte/param)13 GB · Single GPU (<24 GB)
INT4 (0.5 bytes/param)6.4 GB · Single GPU (<24 GB)

Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.

All variants

23 variants

Lineage

Original model Family: meta-llama/Llama-3.2 23 derivatives on the Hub

finetune: 9quantized: 3adapter: 11

Top variants (23 shown, ranked by downloads)

Relation
Quant
Size
23 rows
Variant Relation Quant Params Band License Author Likes Downloads
unsloth/Llama-3.2-11B-Vision finetune — 10.6B L llama3.2 unsloth 34 27.6k
unsloth/Llama-3.2-11B-Vision-bnb-4bit quantized -bnb 10.9B L llama3.2 unsloth 19 20.4k
unsloth/Llama-3.2-11B-Vision-unsloth-bnb-4bit quantized -bnb 10.9B L llama3.2 unsloth 5 17.3k
impactframes/Llama-3.2-11B-Vision-bnb-4bit quantized -bnb 10.9B L llama3.2 impactframes 0 1.6k
shashikanth-a/Llama-3.2-11B-Vision-4bit finetune -4bit 7.06B M llama3.2 shashikanth-a 2 1.3k
PKU-Alignment/Beaver-Vision-11B finetune — — — apache-2.0 PKU-Alignment 2 939
Infernaught/mllama-3.2-11b-10-epochs adapter — — — — Infernaught 1 65
Mahesh-janu/vision-textile finetune — 124M S llama3.2 Mahesh-janu 0 107
avi1057/lora adapter — — — llama3.2 avi1057 0 70
yilin-wu/lora adapter — — — llama3.2 yilin-wu 0 62
aruboi/llama-32-11b-vision_model_output22 finetune — — — llama3.2 aruboi 0 62
masud99r/lora adapter — — — llama3.2 masud99r 0 53
mgertner/lora adapter — — — llama3.2 mgertner 0 47
kvu0/VQA adapter — — — — kvu0 0 40
aruboi/llama-32-11b-vlm_peft_output33 adapter — — — llama3.2 aruboi 0 38
tangy0/lora adapter — — — llama3.2 tangy0 0 26
a22aniket/paligemma_vqav2 adapter — — — llama3.2 a22aniket 0 24
mgertner/llama-collegiate2 adapter — — — — mgertner 0 24
Infernaught/mllama-11b-vision-lora adapter — — — — Infernaught 0 23
igoruehara/llama finetune — — — mit igoruehara 0 0
CHENG678/Llama3.2_11B finetune — — — llama3.2 CHENG678 0 0
harshg9/Llama-3.2-Test-A finetune — — — llama3.2 harshg9 0 0
Adignite/Llama-3.2-11B-Vision-image_tuned finetune — — — mit Adignite 0 0

Articles and coverage

25 pieces

Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.

Official2

Llama 3.2: Revolutionizing edge AI and vision with open, customizable models
ai.meta.com2024-09-25officialauthorityHN front pageabout the Llama 3.2 familyHN 924 pts · 328 comments2,460 words
Meta releases Llama 3.2, featuring small and medium-sized vision LLMs (11B and 90B) alongside lightweight text-only models (1B and 3B) designed for edge and mobile devices. The 11B and 90B models serve as drop-in replacements for their corresponding text model equivalents while the 1B and 3B models support a context length of 128K tokens and are enabled on day one for Qualcomm and MediaTek hardware. Both pre-trained and aligned vision models are available for fine-tuning using torchtune and local deployment via torchchat, with weights based on BFloat16 numerics.written, reviewed, cited
  • The 11B and 90B vision models require an entirely new model architecture that supports image reasoning.
  • Developers can keep all text-only capabilities intact because the adapter training intentionally did not update the language-model parameters.
  • The 1B and 3B models are created by using structured pruning in a single shot manner from the Llama 3.1 8B.
Llama 3.2 released: Multimodal, 1B to 90B sizes
llama.com2024-09-25officialauthorityabout the Llama 3.2 familyHN 89 pts · 19 comments42 words

Analysis8

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders
github.com2024-11-21authorityHN front pageabout the Llama 3.2 familyHN 579 pts · 99 comments5,768 words
The project trained a Sparse Autoencoder on 6.5 Billion activations from Llama 3.2-3B layer 23 over 10 epochs. Data capture processed 25 million sentences totaling 4TB of raw activation data compressed to 3.2TB.generated, cited
I Self-Hosted Llama 3.2 with Coolify on My Home Server
geek.sg2024-10-16HN front pageabout the Llama 3.2 familyHN 221 pts · 90 comments2,289 words
A guide details self-hosting Llama 3.2 on a home server using Coolify and Ollama. The author achieved a 10x reduction in inference time by enabling GPU acceleration on an NVIDIA GeForce RTX 2060 using the CUDA toolkit and nvidia-container-toolkit. The setup involves installing Ubuntu 24, configuring Cloudflare Tunnels, and managing CUDA toolkits.written, reviewed, cited
  • Anyone with physical access can read your data if you avoid LVM or disk encryption for smoother reboots.
  • Cloudflare provides free SSL certificates only for wildcard domains at the top level, not on subdomains.
  • The Ollama service initially runs on the CPU until the NVIDIA Container Toolkit is installed and configured.
Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy
github.com2026-06-23authorityabout the Llama 3.2 familyHN 2 pts · 0 comments196 words
A minimal implementation of Llama 3.2 Instruct inference runs in ~100 lines of pure Numpy code. The project supports Python ≥ 3.10 and includes backends for PyTorch and Jax alongside the primary Numpy version. Ingredients in Llama 3.2 include RoPE with the Llama-3 frequency scaling, GQA, RMSNorm, SwiGLU MLP, and a shared unembedding / embedding matrix.written, reviewed, cited
Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally
ollama.com2024-11-06HN front pageabout the Llama 3.2 familyHN 182 pts · 25 comments202 words
Llama can now see and run on your device – welcome Llama 3.2
huggingface.co2024-09-25authorityabout the Llama 3.2 familyHN 26 pts · 1 comments3,434 words
Verbatim AI – on-device transcription (Whisper) + summaries (Llama 3.2)
apps.apple.com2026-04-21about the Llama 3.2 familyHN 2 pts · 1 comments
Llama 3.2 Release
github.com2024-09-25authorityabout the Llama 3.2 familyHN 12 pts · 0 comments
Load Llama-3.2 WebGPU in the browser from a local folder
simonwillison.net2025-09-09authorityabout the Llama 3.2 familyHN 3 pts · 0 comments
All coverage tracked for this model (25) — append-only, nothing is ever removed
TitleSourcePublishedFirst seenSignals
Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPygithub.com2026-06-232026-10-07hn
Verbatim AI – on-device transcription (Whisper) + summaries (Llama 3.2)apps.apple.com2026-04-212026-10-07hn
Show HN: Llama 3.2 3B and Keiro Research achieves 85% on SimpleQAkeirolabs.cloud2026-03-072026-10-07hn
RWKV-7 beats Llama 3.2 with 3x fewer training tokens and formally exceeds TC^0ai.gopubby.com2026-02-232026-10-07hn
Show HN: Recall – open-source local file organizer using Llama 3.2 and Ollamagithub.com2025-12-102026-10-07hn
Load Llama-3.2 WebGPU in the browser from a local foldersimonwillison.net2025-09-092026-10-07hn
Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcriptsbilawal.net2025-09-012026-10-07hn
Show HN: MLX.zig – Llama 3.2 in Ziggithub.com2025-03-142026-10-07hn
Run Llama 3.2 3B on your phoneapps.apple.com2025-01-182026-10-07hn
I built this robot and gave it a llama3.2 braintwitter.com2025-01-142026-10-07hn
PydanticAI using Ollama (llama3.2) running locallygithub.com2024-12-062026-10-07hn
Show HN: Llama 3.2 Interpretability with Sparse Autoencodersgithub.com2024-11-212026-10-07hn
Show HN: Finetune Llama 3.2 Vision in a Colabcolab.research.google.com2024-11-212026-10-07hn
LLama3.2-vision as almost perfect OCR?demo.doctractor.com2024-11-182026-10-07hn
Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locallyollama.com2024-11-062026-10-07hn
I Self-Hosted Llama 3.2 with Coolify on My Home Servergeek.sg2024-10-162026-10-07hn
Implementing the Llama 3.2 1B and 3B Architectures from Scratchgithub.com2024-10-052026-10-07hn
Llama can now see and run on your device – welcome Llama 3.2huggingface.co2024-09-252026-10-07hn
Open Source wireframe to app powered by Llama 3.2 Visionnapkins.dev2024-09-252026-10-07hn
Llama 3.2 1B and 3B on-device modelstwitter.com2024-09-252026-10-07hn
Llama 3.2: Lightweight models for edge devicestwitter.com2024-09-252026-10-07hn
Llama 3.2 Releasegithub.com2024-09-252026-10-07hn
Llama 3.2: Revolutionizing edge AI and vision with open, customizable modelsai.meta.com official2024-09-252026-10-07hn
Download Llama 3.2 1B, 3B, 11B, 90Bllama.com official2024-09-252026-10-07hn
Llama 3.2 released: Multimodal, 1B to 90B sizesllama.com official2024-09-252026-10-07hn

Papers

1 paper

Papers 1

arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).

Similar models

3 models

Similar models

  • Qwen3.5-9B · 9.65B
    same size band (L), same task (image-text-to-text), more providers, permissive license
  • GLM-4.6V-Flash · 10.3B
    same size band (L), same task (image-text-to-text), more providers, permissive license
  • Qwen3-VL-8B-Instruct · 8.77B
    same task (image-text-to-text), more providers, permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:39 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:10 UTC · Last verified 2026-10-25

Follow Llama-3.2-11B-Vision

Watch this model

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.