Skip to main content
πŸ“– The AI Tool Bible

AI tools linked to Phi-4

Phi-4 is a model from Microsoft. 7 tools in this directory are linked to it.

Each tool is listed because text on its own profile, or on its own website or documentation (quoted on its card with the page it comes from), names Phi-4 by its exact name. That is a keyword match, not a test: a tool that names several models may not run this one in every plan or version, so read the quoted text and check the tool before relying on it.

Tools linked to Phi-4

  • LM StudioAgents

    LM Studio Bionic is a natively local agent for open models built for creativity, work, and code.

    Its site says: β€œphi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books” source page

  • RunPodFine-tuning

    Its site says: β€œRun microsoft/phi-4 with a custom API endpoint” source page

  • vLLMFine-tuning

    Open-source high-throughput inference engine for serving LLMs with PagedAttention and continuous batching.

    Its site says: β€œ| microsoft/Phi-4-mini-instruct , microsoft/Phi-4 , microsoft/Phi-3-mini-4k-instruct , microsoft/Phi-3-mini-128k-instruct , microsoft/Phi-3-medium-128k-instruct , etc.” source page

  • LLaMA FactoryFine-tuning

    Open-source, no-code WebUI for fine-tuning 100+ open LLMs with LoRA, QLoRA, DPO, and PPO.

    Its site says: β€œ[25/01/10] We supported fine-tuning the **[Phi-4](https://huggingface.co/microsoft/phi-4)** model.” source page

  • OllamaCoding

    The de facto runtime for running open-weights LLMs locally, now with a paid cloud tier for bigger models.

    Its site says: β€œPhi-4 is a 14B parameter, state-of-the-art open model from Microsoft.” source page

  • AirLLMFine-tuning

    AirLLM 2.8T LLM inference with single 4GB GPU

    Its site says: β€œRun **DeepSeek-V3 (671B) on ~12GB** and **Qwen3-235B on ~3GB**, plus Qwen3, Llama 3.x/4, DeepSeek V2/V3, Phi-4, Gemma and more β€” all through a single `AutoModel`.” source page

  • Toolkit for Enterprise RAG Pipelines with Small, Specialized Models

    Its site says: β€œ- New Models added to ModelCatalog, including phi-4, Deepseek-Qwen-7B, Deepseek-Qwen-14B, and many others” source page

Official pages:Vendor page β†’Hugging Face β†’

All models Β· Browse every AI tool