This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks

cookbook slm language-model phi3 phi3-vision phi3-testing small-language-model phi-4 phi4 phi4-mini phi4-multimodal phi-4-mini phi-4-multimodal

• Updated Nov 2, 2026
• Jupyter Notebook

1 API key. 220,000+ AI models. Bytez is the largest serverless Model Inference API on the internet. Let's build ✨

api opensource serverless mistral llms multimodla deepseek llama3 bytez phi4

• Updated Mar 3, 2026
• TypeScript

Local CLI Copilot, powered by Ollama. 💻🦙

bash zsh powershell llm llama3 qwen2-5 phi4 deepseek-r1

• Updated Feb 22, 2026
• Go

✨ AI interface for tinkerers (Ollama, Haystack RAG, Python)

agent embedding rag huggingface hugging-face llm llm-inference ollama ollama-client ollama-gui ollama-api deepseek-chat deepseek llama3 agentic-ai retrival-augmented-generation phi4 deepseek-r1

• Updated May 19, 2026
• Python

Super lightweight Ollama + Qwen Code alternative to run Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

agent cli coding llama agents gemma mistral llm llms llava llama2 ollama qwen deepseek llama3 phi4 gemma3 gemma3n

• Updated Dec 24, 2025
• TypeScript

Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.

c cpp self-hosted llama gpt gemma mistral llm llms llava llamacpp localai llama2 qwen deepseek llama3 phi3 gemma2 phi4 gemma3

• Updated May 22, 2025
• C++

Pivotal Token Search

tokens dataset-generation sae sparse-autoencoder dpo llm reasoning-agent llm-inference direct-preference-optimization llm-steering steering-vector phi-4 reasoning-language-models phi4 reasoning-models mech-interp phi4-mini phi-4-mini pivotal-token-search pivotal-tokens

• Updated Nov 7, 2026
• Python

Kolosal AI is an OpenSource and Lightweight alternative to Ollama to run LLMs 100% offline on your device.

c cpp llama gemma mistral llm llms llava llama2 ollama qwen deepseek llama3 phi4 gemma3 gemma3n

• Updated Jan 2, 2026
• C++

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

go golang llama gemma mistral llm llms llava llama2 ollama deepseek llama3 phi3 gemma2 phi4

• Updated Nov 10, 2026
• Dockerfile

💬 A CLI app that lets you watch conversations between two LLMs (all running locally using Ollama)

python ai chatbot debate ai-demo large-language-models llm chatgpt ollama llama3 ai-simulation ai-conversation phi4 python-llm granite3

• Updated Jun 14, 2025
• Python

Comprehensive benchmark of 44 open source language models across creative writing, logic puzzles, counterfactual reasoning, and programming tasks. Tested on Apple M4 Max with detailed performance analysis.

open-source benchmark programming puzzle writing mlx cogito counterfactual llm ollama llama3 phi4 gemma3 qwen3 llama4 granite3

• Updated Jun 13, 2025
• Python

Docker service stack for a comprehensive local ai experience, running on a normal home hardware setup with single GPU. Project-Status: Working, Backlog.

docker devops docker-compose grafana gemma stable-diffusion comfyui local-ai ollama qwen open-webui stable-audio flux-dev flux-schnell phi4 deepseek-r1 devstral wan22 gpt-oss saladtechnologies

• Updated May 11, 2026
• Python

Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.

rust typescript self-hosted llama gpt gemma mistral tauri llm llms llamacpp localai llama2 qwen deepseek llama3 phi3 gemma2 phi4 gemma3

• Updated Jun 12, 2025
• Svelte

An OpenAI/Gemini Deep Research equivalent that you can run locally

agent research local-llm deepseek llama3 phi4

• Updated Feb 13, 2025
• Jupyter Notebook

Build multi-step AI workflows with schema-guided reasoning. Supports Ollama, LMStudio, OpenAI, OpenRouter, Gemini, and all latest models for structured generation, chaining, and data processing.

dataset synthetic-data synthetic-dataset-generation jsonl llm localllm ollama ai-workflow lmstudio llama3 agentic-ai phi4 deepseek-r1

• Updated Nov 9, 2026
• Go

Code for Paper Submitted in GRADES-NDA 2025

python python3 mistral property-graphs large-language-models prompt-engineering llms ollama gemma2 llama3-2 qwen2-5 phi4 deepseek-r1 graph-repair

• Updated Aug 11, 2025
• Python

AI‑powered adaptive cognitive rehabilitation platform with personalized cognitive games, wellness activities, and therapist monitoring.

ai healthcare wellness neuropsychology blazor phi4 dotnet10 ai-cognitive-rehabilitation

• Updated May 18, 2026
• HTML

A Python toolkit using LLMs (like Microsoft's phi-4 via Nebius API) to generate creative story ideas across genres and write complete short stories, featuring chapter mode for longer narratives.

python llm generative-ai storygeneration nebius phi4

• Updated Apr 22, 2025
• Python

OllamaLLM Desktop App. Golang API. Utilizes 10 LLMs. ChatGPT-like GUI . In it's current form, it operates as a desktop app / local host API, but, has the foundation to be scaled up to become a complete web app. See the documentation for more.

javascript golang ai shell-script mistral aiassistant large-language-models aicodeassistant llama3-8b qwen2-5 phi4 deepseek-coder-v2 deepseek-r1-linux gemma3 qwen3 llama4 devstral

• Updated Nov 22, 2025
• JavaScript

Leverage LLM (SLM like phi4) to generate documentation for very large SQL file which has 100's of procedures..

ai slm llm phi4

• Updated Feb 14, 2025
• HTML