# Kanana-2-v-decide by Kakao > Kanana-2-v-decide from Kakao scores text and images with cached candidate embeddings. Check its token limits, custom runtime and licence terms. Updated 2026-11-07 (Australia/Adelaide) ## Quick answers ### What is Kanana-2-v-decide by Kakao? [Kanana-2-v-decide](): A text/image decision model built on Kanana-2-v-3b. [Kanana-2-v-decide facts]() [Source]() ### Who makes Kanana-2-v-decide? [Kanana-2-v-decide](): Kakao [Kanana-2-v-decide facts]() [Source]() ### Are Kanana-2-v-decide's weights open? [Kanana-2-v-decide](): Public weights, custom Transformers code and /v1/systemone server Licence: Kanana Open License [Kanana-2-v-decide facts]() [Source]() By Kakao · Weights upload: 2026-11-06 · OPEN A text/image decision model built on Kanana-2-v-3b. It compares state/question embeddings with candidate embeddings and returns option probabilities. Candidate embeddings can be cached. The supplied HTTP server processes one request at a time. ## Facts - Size: 3.67B: 3.18B language model and 0.49B vision encoder - Inputs: Korean or English text, JSON or chat; up to 10 images; no video - Context: 20,480 tokens; overlong inputs are shortened by default, or rejected with --strict-inputs - Licence: Kanana Open License - Access: Public weights, custom Transformers code and /v1/systemone server ## Claims and sources - **VENDOR-REPORTED**: Kakao reports 61.34 on public Decision Index text and 61.12 on vision, averaging 61.23 across those two scores. Its Korean benchmark score is 72.50 over 15,909 questions. These are maker results, not a combined ranking of all decision models. [source]() ## Links - [Source: Model card and weights]() ## Related projects No related projects are listed in the registry.