Kanana Nano 2.1B Embedding is an open-source language model by kakaocorp. Features: 2.1b LLM, VRAM: 4.2GB, Context: 8K, License: cc-by-nc-4.0, LLM Explorer Score: 0.21.
Arxiv:2502.18934 Conversational Custom code En Feature-extraction Kanana2vec Ko Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/kakaocorp/kanana-nano-2.1b-embedding
Kanana Nano 2.1B Embedding 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 Nano 2.1B Embedding Parameters and Internals
| LLM Name | Kanana Nano 2.1B Embedding |
| Repository 🤗 | https://huggingface.co/kakaocorp/kanana-nano-2.1b-embedding |
| Model Size | 2.1b |
| Required VRAM | 4.2 GB |
| Updated | 2026-04-09 |
| Maintainer | kakaocorp |
| Model Type | kanana2vec |
| Model Files | |
| Supported Languages | en ko |
| Model Architecture | Kanana2VecModel |
| License | cc-by-nc-4.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.49.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Rank the Kanana Nano 2.1B Embedding 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? 52658 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a