phi4

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

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

Automatable GenAI Scripting

Local CLI Copilot, powered by Ollama. 💻🦙

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

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

Pivotal Token Search

Use 150k+ serverless AI models through a unified API. Deploy, stream, and compare in seconds — fast, affordable, production-ready. ✨

LLMs in flax.NNX to run on any hardware backend

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

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

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

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

Scalytics Connect, the Operation Stack for Open Models, Community Edition - get running in an easy way with open models

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

Code for Paper Submitted in GRADES-NDA 2025

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.

Generate synthetic datasets using local LLMs via Ollama and LMstudio with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other major language models.

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

AI Chat (Codaweb AI) written in NextsJS 15 with multiple LLMs models ( DeepSeek, DeepCode, Perplexity, Gemini and Phi-4)