Arxiv:2502.18934 Autotrain compatible Conversational En Endpoints compatible Instruct Ko Mixtral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/kakaocorp/kanana-1.5-15.7b-a3b-instruct
Kanana 1.5 15.7B A3b 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 1.5 15.7B A3b Instruct Parameters and Internals
| LLM Name | Kanana 1.5 15.7B A3b Instruct |
| Repository 🤗 | https://huggingface.co/kakaocorp/kanana-1.5-15.7b-a3b-instruct |
| Model Size | 15.7b |
| Required VRAM | 31.4 GB |
| Updated | 2025-09-29 |
| Maintainer | kakaocorp |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en ko |
| Model Architecture | MixtralForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.51.1 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128259 |
| Torch Data Type | bfloat16 |
Rank the Kanana 1.5 15.7B A3b 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124