Language model
Llama-3.2-90B-Vision-Instruct
Meta
- Released
- September 25, 2024
- Data date
- October 28, 2026
- Benchmark-Meta-Score
- UnavailableNo independent results
- Input
- Text, Image
- Output
- Text
Llama 3.2 90B Vision Instruct combines text and image input with text output. The catalog lists 88.8 billion parameters and 128,000 context tokens. Meta publishes this instruction-tuned vision variant under the Llama 3.2 Community license.
Specifications and access
Popularity
29.1 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Input | Documented modalities. Retrieved October 27, 2026. |
| Output | Documented modalities. Retrieved October 27, 2026. |
| Research status | Research date October 28, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | Maximum output Note Meta documents 128K context but no separate maximum generation length for this exact vision instruction checkpoint. |
| Additional source | Hugging Face (retrieved October 28, 2026) · Llama 3.2 90B Vision Instruct model card · Editorial description reviewed October 29, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |