Arxiv:2404.14219 Arxiv:2409.12136 Arxiv:2506.18349 Conversational Custom code En Instruct Moe Phimoe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/microsoft/Phi-tiny-MoE-instruct
Phi Tiny MoE 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)
Phi Tiny MoE Instruct Parameters and Internals
| LLM Name | Phi Tiny MoE Instruct |
| Repository 🤗 | https://huggingface.co/microsoft/Phi-tiny-MoE-instruct |
| Model Size | 3.8b |
| Required VRAM | 7.5 GB |
| Updated | 2026-01-10 |
| Maintainer | microsoft |
| Model Type | phimoe |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | PhiMoEForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.43.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Rank the Phi Tiny MoE 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? 51585 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124