Phi 2 4bit 64rank is an open-source language model by LoftQ. Features: 2.8b LLM, VRAM: 5.6GB, Context: 2K, License: mit, Quantized, LLM Explorer Score: 0.12.
| 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 | 2026-08-07 |
| 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 |
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 | 8 | 0 |
| MFANN3bv0.24 | 128K / 11.1 GB | 6 | 0 |
| MFANN3b | 128K / 11.1 GB | 86 | 0 |
| MFANN3bv1.4 | 128K / 11.1 GB | 8 | 0 |
| MFANN Phigments Slerp V3.2 | 128K / 5.6 GB | 6 | 0 |
| MFANN3bv1.3 | 128K / 11.1 GB | 14 | 0 |
| MFANN3bv0.23 | 128K / 11.1 GB | 10 | 0 |
| MFANN3bv1.1 | 128K / 11.1 GB | 10 | 0 |