8bit Autotrain compatible Code Conversational Custom code Instruct Mlx Moe Multilingual Phimoe Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Phi-3.5-MoE-instruct-8bit
Phi 3.5 MoE Instruct 8bit 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 3.5 MoE Instruct 8bit Parameters and Internals
| Model Type |
| |
| Supported Languages |
|
| LLM Name | Phi 3.5 MoE Instruct 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Phi-3.5-MoE-instruct-8bit |
| Model Size | 11.8b |
| Required VRAM | 44.5 GB |
| Updated | 2025-01-22 |
| Maintainer | mlx-community |
| Model Type | phimoe |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | PhiMoEForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|end|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Rank the Phi 3.5 MoE Instruct 8bit 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? 41728 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227