Model Card on HF 🤗: https://huggingface.co/AdithyaVardan/Quantised-Phi-2
Quantised Phi 2 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)
Quantised Phi 2 Parameters and Internals
| LLM Name | Quantised Phi 2 |
| Repository 🤗 | https://huggingface.co/AdithyaVardan/Quantised-Phi-2 |
| Model Size | 600.5m |
| Required VRAM | 1.8 GB |
| Updated | 2025-08-20 |
| Maintainer | AVMLegend |
| Model Type | phi |
| Model Files | |
| Model Architecture | PhiForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.39.0 |
| Tokenizer Class | CodeGenTokenizer |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
Best Alternatives to Quantised Phi 2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Quantised Phi 2 | 2K / 1.8 GB | 8 | 0 |
| Phi 2 Quantize Gptq | 2K / 1.8 GB | 3 | 2 |
| ... 2 Electrical Engineering GPTQ | 2K / 1.8 GB | 13 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than AdithyaVardan/Quantised-Phi-2 .
Rank the Quantised Phi 2 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? 50767 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124