Arxiv:2310.08659 4bit Autotrain compatible Custom code En Endpoints compatible Lora Phi Quantization Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoftQ/phi-2-4bit-64rank
Phi 2 4bit 64rank 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 4bit 64rank Parameters and Internals
| LLM Name | Phi 2 4bit 64rank |
| Repository 🤗 | https://huggingface.co/LoftQ/phi-2-4bit-64rank |
| Model Size | 2.8b |
| Required VRAM | 5.6 GB |
| Updated | 2025-09-23 |
| Maintainer | LoftQ |
| 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 | 4.39.3 |
| Tokenizer Class | CodeGenTokenizer |
| Vocabulary Size | 51200 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
Best Alternatives to Phi 2 4bit 64rank
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Bnb DPO 8bit | 2K / 3 GB | 7 | 0 |
| Bnb DPO 8bit | 2K / 3 GB | 7 | 0 |
| Phi 2 Nf4 Fp16 Upscaled | 2K / 5.6 GB | 9 | 0 |
| MFANN3bv0.24 | 128K / 11.1 GB | 5 | 0 |
| MFANN3b | 128K / 11.1 GB | 5 | 0 |
| MFANN3bv1.4 | 128K / 11.1 GB | 6 | 0 |
| MFANN Phigments Slerp V3.2 | 128K / 5.6 GB | 5 | 0 |
| MFANN3bv1.3 | 128K / 11.1 GB | 6 | 0 |
| MFANN3bv0.23 | 128K / 11.1 GB | 5 | 0 |
| MFANN3bv1.1 | 128K / 11.1 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than LoftQ/phi-2-4bit-64rank .
Rank the Phi 2 4bit 64rank 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124