Model Card on HF 🤗: https://huggingface.co/radames/phi-2-quantized
Phi 2 Quantized 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 Quantized Parameters and Internals
| LLM Name | Phi 2 Quantized |
| Repository 🤗 | https://huggingface.co/radames/phi-2-quantized |
| Base Model(s) | |
| Required VRAM | 1.6 GB |
| Updated | 2025-09-23 |
| Maintainer | radames |
| Model Type | phi-msft |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | PhiForCausalLM |
| Transformers Version | 4.35.2 |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
| Activation Function | gelu |
Best Alternatives to Phi 2 Quantized
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MFANN3bv0.7.10 GGUF | 2K / 1.6 GB | 11 | 0 |
| Candle Phi 1 | 2K / 2.8 GB | 62 | 0 |
| Candle Phi 1 5 | 2K / 2.8 GB | 49 | 0 |
| Phi 2 GGUF | 2K / 1.1 GB | 78 | 2 |
| Phi 1 5 GGUF | 0K / 0.6 GB | 601 | 6 |
| Dolphin 2 6 Phi 2 Candle | 0K / 0 GB | 39 | 4 |
| Phi 1 5 Q4 | 2K / GB | 3 | 1 |
| Phi 2 Hf 4bit Mlx | 2K / 1.8 GB | 182 | 1 |
| Merlin1.4 | 2K / 5.6 GB | 5 | 0 |
| Merlin1.2 | 2K / 5.6 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than radames/phi-2-quantized .
Rank the Phi 2 Quantized 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? 51560 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124