Model Card on HF 🤗: https://huggingface.co/mlx-community/phi-2-hf-4bit-mlx
Phi 2 Hf 4bit Mlx 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 2 Hf 4bit Mlx Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Phi 2 Hf 4bit Mlx |
| Repository 🤗 | https://huggingface.co/mlx-community/phi-2-hf-4bit-mlx |
| Required VRAM | 1.8 GB |
| Updated | 2025-10-31 |
| Maintainer | mlx-community |
| Model Type | phi |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | PhiForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.36.2 |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
Best Alternatives to Phi 2 Hf 4bit Mlx
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 1 5 Q4 | 2K / GB | 3 | 1 |
| Merlin1.4 | 2K / 5.6 GB | 5 | 0 |
| Merlin1.2 | 2K / 5.6 GB | 5 | 0 |
| Phi1.5 Quantized 2 | 2K / GB | 5 | 0 |
| Merlin1.5 | 2K / 5.6 GB | 5 | 0 |
| Merlin1.3 | 2K / 5.6 GB | 5 | 0 |
| Tinyllama Quant | 2K / 0.8 GB | 10 | 1 |
| Phi1.5 Update 4 | 2K / GB | 6 | 0 |
| Phi 2 Fp8 | 2K / 3.3 GB | 89 | 0 |
| Phi 2 Fp8 | 2K / 3.3 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/phi-2-hf-4bit-mlx .
Rank the Phi 2 Hf 4bit Mlx 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? 51562 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124