Model Card on HF 🤗: https://huggingface.co/ktotam/phi-2-4b
Phi 2 4B 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 4B Parameters and Internals
| LLM Name | Phi 2 4B |
| Repository 🤗 | https://huggingface.co/ktotam/phi-2-4b |
| Model Size | 4b |
| Required VRAM | 1.8 GB |
| Updated | 2025-10-05 |
| Maintainer | ktotam |
| Model Type | phi |
| Model Files | |
| Model Architecture | PhiForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | CodeGenTokenizer |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
Best Alternatives to Phi 2 4B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...hi 2 Upscaled 4B Instruct V0.1 | 2K / 8.1 GB | 4 | 3 |
| Delta 4B Super | 2K / 9.3 GB | 5 | 0 |
| Delta 4B Orange | 2K / 9.3 GB | 7 | 0 |
| Delta 4B Notso Base | 2K / 9.3 GB | 62 | 0 |
| Delta 4B Instruct V0.1 | 2K / 9.4 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ktotam/phi-2-4b .
Rank the Phi 2 4B 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? 51564 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124