Tasks and inputs
Kanana-2 Vision Encoder is listed for Image feature extraction, Document OCR. It accepts image and produces embedding. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Nov 19, 2026
Kakao's kanana-2-vision-encoder comes in 426M medium and 98M tiny sizes: open native-resolution image encoders for building Korean-strong VLMs.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Pricing conditions: Open weights for self-hosting; no hosted API price. Hardware cost is yours.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Kakao's kanana-2-vision-encoder series answers a narrow question that matters to anyone building a vision-language model: which image encoder should sit in front of the language model? Kakao released two answers on 21 October 2026, a 426M-parameter medium and a 98M-parameter tiny, both open and both tuned with Korean documents and culture in mind.
They extract features only. There is no text generation module; you attach your own LLM through a projector or patch merger.
Every encoder was paired with Kanana-2 1.3B Instruct through a patch merger and trained and evaluated under identical conditions, across 42 benchmarks in nine categories, with each category weighted equally in the average.
| Scale | Encoder | Average (9 categories) |
|---|---|---|
| ~0.4B | kanana-2-vision-encoder-medium (426M) | 55.62 |
| ~0.4B | PE-Lang-L14-448 (291M) | 51.54 |
| ~0.4B | Qwen3.5 encoder (415M) | 50.51 |
| ~0.4B | SigLIP2 so400m naflex (412M) | 49.77 |
| ~0.1B | kanana-2-vision-encoder-tiny (98M) | 51.81 |
| ~0.1B | Qwen3.5-0.8B encoder (88M) | 49.62 |
| ~0.1B | SigLIP2 base naflex (86M) | 46.81 |
The biggest gains sit where you would expect: Korean OCR and documents (medium scores 86.80 on KoOCRBench), chart reading, and visual grounding, where medium reaches 79.88 on CountBenchQA. On some general English benchmarks such as MMBench the comparison encoders are level or ahead. These are Kakao's numbers.
One more detail stands out. Even the 98M tiny encoder beats every 0.4B rival in the table on average.
Install torch, torchvision, pillow and transformers, load with AutoImageProcessor and AutoModel with custom code, and you get a tensor of shape (total patches, feature dim). Both repos carry the same documentation, so the choice is purely about size.
Tiny suits on-device or high-throughput VLMs; medium suits document-heavy assistants. Run both behind the same small LLM on a sample of your real images, especially Korean receipts or forms if that is your market, and compare OCR accuracy before committing to a full VLM training run.
Weights are under the Kanana Open License. Kakao's Kanana-2 V Decide 3B shows the family's multimodal direction; more encoders are in the image feature extraction directory.
Compare the model on the work you need to complete.
Kanana-2 Vision Encoder is listed for Image feature extraction, Document OCR. It accepts image and produces embedding. Use the publisher’s input format and preprocessing for your chosen deployment.
Evaluate retrieval over a labelled query set. Keep the encoder, vector dimensions and index settings consistent.
The weights are downloadable under Kanana Open License. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
allenai
OlmoEarth v1.3 Base is Ai2's open Earth-observation model that turns a year of Sentinel and Landsat imagery into a 128-dimension embedding per 10 m pixel.
bioptimus
Hugging Face repository for Image feature extraction.
bioptimus
Hugging Face repository for Image feature extraction.
camenduru
camenduru/dinov3-vitl16-pretrain-lvd1689m is a source-linked Hugging Face repository assigned to Image feature extraction. Its recorded task interface accepts image and produces embeddings.
F1nnSBK
Hugging Face repository for Image feature extraction.
facebook/dinov2-base is a source-linked Hugging Face repository assigned to Image feature extraction. Its recorded task interface accepts image and produces embeddings.