Meta model product
Llama 3.2 11B
2 11B Vision Instruct is an instruction-tuned multimodal large language model optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.
Updated Aug 12, 2026. Default version: Llama 3.2 11B Instruct
LLMBoard score0.0Llama 3.2 11B Instruct
Coverage60%10 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Llama 3.2 11B Specifications
Technical details for the model's default version.
- Version
- Llama 3.2 11B Instruct
- Released
- Sep 25, 2024
- Knowledge cutoff
- Dec 31, 2023
- Parameters
- 10.6B
- Context window
- 128K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Llama 3.2 Community License
Llama 3.2 11B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Llama 3.2 11B Benchmark Results
Benchmark scores for Llama 3.2 11B Instruct.
Llama 3.2 11B Arena Results
Preference and agent-evaluation results for the default version.
| vision | overall | 135 | 966.5 | 4,817 | N/A | |
| vision style control | overall | 137 | 992.9 | 4,817 | N/A |
Llama 3.2 11B Runtime Performance
Provider-specific output speed and catalog latency for Llama 3.2 11B Instruct. Runtime does not affect the capability score.
| Together | 168 tok/s | 0.5 s | 128K | 128K | |
| Fireworks | 125 tok/s | 0.2 s | 128K | 128K | |
| DeepInfra | 108 tok/s | 0.5 s | 128K | 128K | |
| Sambanova | 100 tok/s | 0.5 s | 128K | 128K | |
| Bedrock | 100 tok/s | 0.5 s | 128K | 128K | |
| Groq | 100 tok/s | 0.5 s | 128K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Llama 3.2 11B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.07 input, $0.33 output per 1M via LLM Gateway
- Tracked offerings
- 1
| LLM Gateway | llama-3.2-11b-instruct | global | $0.07 | $0.33 | 128K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Llama 3.2 11B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Llama 3.2 11B Instruct | 0.0 | 10.6B | 128K | 128K | No | Llama 3.2 Community License |
What is Llama 3.2 11B?
Key information about Llama 3.2 11B and its available data.
2 11B Vision Instruct is an instruction-tuned multimodal large language model optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. It accepts text and images as input and generates text as output.
Data as of 2026-08-11.
Llama 3.2 11B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Llama 3.2 11B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
Llama 3.2 3B
Meta
ME
Llama 3.1 8B
Meta
ME
Llama 3.2 90B
Meta
ME
Llama 3.1 70B
Meta
ME
Llama 4 Scout
Meta
ME
Llama 3.3 70B
Meta
FAQ
Common questions about Llama 3.2 11B.
When was Llama 3.2 11B released?
Llama 3.2 11B's default version was released on Sep 25, 2024.
How much does Llama 3.2 11B cost?
No official standard PAYG price is currently available for Llama 3.2 11B. The lowest tracked third-party offer starts at $0.07 input and $0.33 output via LLM Gateway.
Who created Llama 3.2 11B?
Llama 3.2 11B was created by Meta.
What is the context window for Llama 3.2 11B?
The default version has a 128K token context window.
Is Llama 3.2 11B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Llama 3.2 11B?
1 provider offerings are linked to the default version.
What models should I compare Llama 3.2 11B with?
Nearby ranked alternatives include Llama 3.2 3B, Phi 3.5 vision, IBM Granite 4.0 Tiny.