Chapter 02
Phi 模型及其在各平台的可用性
Phi 模型及其在各平台的可用性
边缘与云场景
模型可用性及资源
| Model | 输入 | 内容长度 | Azure AI (MaaS) | Azure ML (MaaP) | ONNX | Hugging Face | Ollama | Nvidia NIM |
| Phi-3-vision-128k-instruct | 文本+图像 | 128k | Playground & Deployment | Playground, Deployment & Finetuning | CUDA,CPU, DirectML | Download | -NA- | NIM APIs |
| Phi-3-mini-4k-instruct | 文本 | 4k | Playground & Deployment | Playground, Deployment & Finetuning | CUDA, Web | Playground & Download | GGUF | NIM APIs |
| Phi-3-mini-128k-instruct | 文本 | 128k | Playground & Deployment | Playground, Deployment & Finetuning | CUDA | Download | -NA- | NIM APIs |
| Phi-3-small-8k-instruct | 文本 | 8k | Playground & Deployment | Playground, Deployment & Finetuning | CUDA | Download | -NA- | NIM APIs |
| Phi-3-small-128k-instruct | 文本 | 128k | Playground & Deployment | Playground, Deployment & Finetuning | CUDA | Download | -NA- | NIM APIs |
| Phi-3-medium-4k-instruct | 文本 | 4k | Playground & Deployment | Playground, Deployment & Finetuning | CUDA, CPU, DirectML | Download | -NA- | NIM APIs |
| Phi-3-medium-128k-instruct | 文本 | 128k | Playground & Deployment | Playground, Deployment & Finetuning | CUDA, CPU, DirectML | Download | -NA- | -NA- |
免责声明：
本文件使用 AI 翻译服务 Co-op Translator 进行翻译。虽然我们力求准确，但请注意，自动翻译可能包含错误或不准确之处。原始文件的母语版本应被视为权威来源。对于重要信息，建议使用专业人工翻译。我们不对因使用本翻译而产生的任何误解或误释承担责任。