Arxiv:2310.06825 Arxiv:2404.14219 Arxiv:2407.21783 Arxiv:2408.00118 Arxiv:2412.15115 Arxiv:2503.19786 Conversational Custom code En Ko Motif Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Motif-Technologies/Motif-2.6B
Motif 2.6B 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)
Motif 2.6B Parameters and Internals
| LLM Name | Motif 2.6B |
| Repository 🤗 | https://huggingface.co/Motif-Technologies/Motif-2.6B |
| Model Size | 2.6b |
| Required VRAM | 10.5 GB |
| Updated | 2025-07-23 |
| Maintainer | Motif-Technologies |
| Model Type | Motif |
| Model Files | |
| Supported Languages | en ko |
| Model Architecture | MotifForCausalLM |
| License | other |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 219520 |
| Torch Data Type | bfloat16 |
Rank the Motif 2.6B 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? 49991 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124