Skip to content

Meta · Chat

Llama 3.2 11B Vision Instruct

Meta 🇺🇸ChatLlama familyOpen weights. One of its sources says the weights are publicly available.
From Cloudflare Workers AI's listing:
The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.
llminfo IQ
92.2
Market median price
$0.06 blended / 1M
Max context
131K
Listings
14

Evidence and sources

🤗 meta-llama/Llama-3.2-11B-Vision-Instruct Model architecture, as its sources state it llminfo IQ 92.2, ranked among chat models. From 59 benchmarks. Plenty of data behind it.How llminfo IQ is computedGood value (56.1). Cheaper per task than its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 18 Sep 2024Maker HQ: US (according to Meta's own website)
Sources: LMArena data, Cloudflare Workers AI, Models.dev data, Hugging FacePrimary data from LMArena from Cloudflare Workers AI: architecture, description from Models.dev: weights availability from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 7 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 3 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionFunction calling

Listings

 Aihubmixmeta-llama/llama-3.2-11b-vision-instruct:free · freeSource: AIHubMix data docsNot published by the provider$0.02$0.02
 Eden AIInference by DeepInfradeepinfra/meta-llama/Llama-3.2-11B-Vision-InstructSource: Models.dev data131K$0.345$0.345
 Flowdotmeta-llama/llama-3.2-11b-vision-instructSource: FlowDot data131K$0.245$0.245
 OpenRoutermeta-llama/llama-3.2-11b-vision-instructSource: GenAI Prices dataNot published by the provider$0.049$0.049
 Cloudflare Workers AI@cf/meta/llama-3.2-11b-vision-instructSources: Cloudflare Workers AI, LiteLLM data, Models.dev data128K$0.0485$0.676
 DeepInfradeepinfra/meta-llama/Llama-3.2-11B-Vision-InstructSource: LiteLLM data131K$0.049$0.049
 Fireworks AIfireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instructSource: LiteLLM data131K$0.20$0.20
 Inference Netmeta/llama-3.2-11b-vision-instructSource: Models.dev data16K$0.055$0.055
 Lambda AIlambda_ai/llama3.2-11b-vision-instructSource: LiteLLM data131K$0.015$0.025
 Novita AImeta-llama/llama-3.2-11b-vision-instructSource: GenAI Prices dataNot published by the provider$0.06$0.06
 Ocioci/meta.llama-3.2-11b-vision-instructSource: LiteLLM data128K$2.00$2.00
 Watsonxwatsonx/meta-llama/llama-3-2-11b-vision-instructSource: LiteLLM data128K$0.35$0.35

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Math

U-MATH7 related benchmarks · 21 results
algebra accuracy
Source: U-MATH and mu-MATH
Task set · algebra · gpt-4o-2024-08-06
differential_calc accuracy
Source: U-MATH and mu-MATH
Task set · differential_calc · gpt-4o-2024-08-06
integral_calc accuracy
Source: U-MATH and mu-MATH
Task set · integral_calc · gpt-4o-2024-08-06
multivariable_calculus accuracy
Source: U-MATH and mu-MATH
Task set · multivariable_calculus · gpt-4o-2024-08-06
overall accuracy
Source: U-MATH and mu-MATH
Task set · u_math · gpt-4o-2024-08-06
precalculus_review accuracy
Source: U-MATH and mu-MATH
Task set · precalculus_review · gpt-4o-2024-08-06
Show 3 more resultsHide 3 results
sequences_series accuracy
Source: U-MATH and mu-MATH
Task set · sequences_series · gpt-4o-2024-08-06

Vision

OCR

Agentic

Human preference

Science

Knowledge

Reasoning

Other

Data credits: OpenVLM Leaderboard (OpenCompass / VLMEvalKit), Apache-2.0 (licence) · LMArena, CC BY 4.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Haq et al., PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language, arXiv:2505.10055v2, CC BY 4.0. Scores extracted from Tables 3-5. (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Toloka, U-MATH and mu-MATH public leaderboard. MIT Space; generated solution outputs retain underlying model terms and are not ingested. (licence)

Around the web

  • Llama 3.2 | Model Cards and Prompt formats - developer.meta.com
    Build with Muse Spark on Meta Model API - now in public preview for US …Build with Muse Spark on Meta Model API - now in public preview for US developers. Get started Stay updated Get started Model Cards & Prompt formats Llama 3.2 Introduction This page covers capabiliti…

    developer.meta.com

  • meta / llama-3.2-1b-instruct
    updatedAt: 2026-08-06T09:58:24.000Z meta / llama-3.2-1b-instruct Model Information The Meta Llama 3.2 collection of multilingual large …updatedAt: 2026-08-06T09:58:24.000Z meta / llama-3.2-1b-instruct Model Information The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pre-trained and instru…

    docs.api.nvidia.com

  • Llama 3.2 Overview — NVIDIA NIM for Vision Language Models (VLMs)
    Skip to main content Back to top NVIDIA NIM for Vision Language Models (VLMs) - …Skip to main content Back to top NVIDIA NIM for Vision Language Models (VLMs) - Home NVIDIA NIM for Vision Language Models (VLMs) - Home NVIDIA NIM for Vision Language Models (VLMs) Choose version Se…

    docs.nvidia.com

  • Llama 3.2 | Model Cards and Prompt formats
    Stay updated Download models Model Cards & Prompt formats Llama 3.2 Introduction This page covers …Stay updated Download models Model Cards & Prompt formats Llama 3.2 Introduction This page covers capabilities and guidance specific to the models released with Llama 3.2: The Llama 3.2 quantized mod…

    llama.com

  • Llama 3.2 3B Instruct - NGC Catalog - NVIDIA
    The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of …The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pre-trained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 …

    catalog.ngc.nvidia.com

  • Llama 3.2 3B Instruct - Lambda
    Skip to main content meta-logo Llama 3.2 3B Instruct Llama 3.2 3B Instruct is a …Skip to main content meta-logo Llama 3.2 3B Instruct Llama 3.2 3B Instruct is a text-generation model designed to process and generate human-like text based on given prompts. It is part of the Llama …

    lambda.ai

  • Llama 3.2 Community License Agreement
    Additional Commercial Terms . If, on the Llama 3.2 version release date, the monthly active …Additional Commercial Terms . If, on the Llama 3.2 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater t…

    llama.com

  • Llama can now see and run on your device - welcome Llama 3.2
    broader collection of languages than the 8 supported languages mentioned above. Developers are encouraged to …broader collection of languages than the 8 supported languages mentioned above. Developers are encouraged to fine-tune Llama 3.2 models for their specific language use cases. Acknowledgements Llama 3…

    huggingface.co

  • meta-llama/Llama-3.2-3B-Instruct · Hugging Face
    scalability. Model Release Date: Sept 25, 2024 Status: This is a static model trained on …scalability. Model Release Date: Sept 25, 2024 Status: This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety. License: Use o…

    huggingface.co

  • meta-llama/Llama-3.2-1B-Instruct · Hugging Face
    offline dataset. Future versions may be released that improve model capabilities and safety. License: Use …offline dataset. Future versions may be released that improve model capabilities and safety. License: Use of Llama 3.2 is governed by the Llama 3.2 Community License (a custom, commercial license agr…

    huggingface.co

Also known as: @cf/meta/llama-3.2-11b-vision-instruct, cloudflare/@cf/meta/llama-3.2-11b-vision-instruct, deepinfra/meta-llama/llama-3.2-11b-vision-instruct, fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct, lambda_ai/llama3.2-11b-vision-instruct, meta-llama/llama-3.2-11b-vision-instruct, meta-llama/llama-3.2-11b-vision-instruct:free, meta/llama-3.2-11b-vision-instruct, nim/meta/llama-3.2-11b-vision-instruct, oci/meta.llama-3.2-11b-vision-instruct, watsonx/meta-llama/llama-3-2-11b-vision-instruct

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works