Kanana 2 3B Instruct is an open-source language model by kakaocorp. Features: 3b LLM, VRAM: 7.1GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.35.
Base model:finetune:kakaocorp/... Base model:kakaocorp/kanana-2-... Conversational Endpoints compatible Instruct Qwen3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/kakaocorp/kanana-2-3b-instruct
Kanana 2 3B Instruct Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Kanana 2 3B Instruct Parameters and Internals
| LLM Name | Kanana 2 3B Instruct |
| Repository 🤗 | https://huggingface.co/kakaocorp/kanana-2-3b-instruct |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 7.1 GB |
| Updated | 2026-07-30 |
| Maintainer | kakaocorp |
| Model Type | qwen3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.57.6 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
Rank the Kanana 2 3B Instruct Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 55501 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a