Models & InferenceBeginner
183kGo+152/daypushed 0d ago
Use it for: Download and run open models like Qwen, DeepSeek, Gemma and gpt-oss locally, and connect them to coding agents and apps.
Quick start
- Install on macOS or Linux with `curl -fsSL https://ollama.com/install.sh | sh` (Windows: `irm https://ollama.com/install.ps1 | iex`)
- Run `ollama` and choose a model to run or an app to connect
- Launch an integration such as `ollama launch claude`
- Use `ollama launch openclaw` for a personal assistant across chat apps
Models & InferenceAdvanced
106kJupyter Notebook+91/daypushed 7d ago
Use it for: Learn how large language models work by coding, pretraining and finetuning a GPT-like model in PyTorch step by step.
Quick start
- git clone --depth 1 https://github.com/rasbt/LLMs-from-scratch.git
- Read the table of contents in the README
- Follow the book chapters alongside the code, step by step
Models & InferenceIntermediate
77.6kPython+74/daypushed 0d ago
Use it for: Run and train LLMs and diffusion models locally through a desktop app that supports GGUF and MLX models.
Quick start
- Download the Unsloth Desktop app for your OS from unsloth.ai/download or GitHub Releases
- Or install manually on macOS/Linux/WSL: curl -fsSL https://unsloth.ai/install.sh | sh
- On Windows run: irm https://unsloth.ai/install.ps1 | iex
- Open the app and pick a model to run or train
Models & InferenceIntermediate
49.5kGo+38/daypushed 0d ago
Use it for: Run LLMs, vision, voice, image and video models on your own hardware behind one OpenAI-compatible API, even without a GPU.
Quick start
- Open the Quickstart at localai.io/basics/getting_started
- Install LocalAI following the documentation
- Pull a model from the models gallery
- Send requests to the local OpenAI-compatible API
Models & InferenceBeginner
37.8kRust+160/daypushed 0d ago
Use it for: Check your CPU, RAM and GPU to see which open-source language models your computer can run well, and at what speed.
Quick start
- Install llmfit for your platform (macOS, Linux or Windows) following the README install section
- Run llmfit so it detects your hardware
- Browse recommended models and quantizations in the terminal interface or web dashboard
- Optionally benchmark a model and share the results via the TUI
Models & InferenceIntermediate
35.5kJupyter Notebook+29/daypushed 1d ago
Use it for: Run very large language models, such as 70B, on a single GPU with as little as 4GB of memory.
Quick start
- Install the airllm package following the Quickstart section
- Load a large model using the example code in the README
- Check the Configurations and MacOS sections for your setup
Models & InferenceIntermediate
34.7kPython+22/daypushed 0d ago
Use it for: Generate images, audio and other outputs in Python using pretrained diffusion models, or train your own diffusion systems.
Quick start
- Create a virtual environment and install PyTorch
- Run: pip install --upgrade diffusers[torch]
- Load a pretrained diffusion pipeline following the README
- Run inference with a prompt to generate output
Models & InferenceAdvanced
11.0kC+++4/daypushed 0d ago
Use it for: Optimize and deploy deep learning models for fast inference on CPUs, Intel GPUs and NPUs, from edge to cloud.
Quick start
- Install OpenVINO from PyPI, Conda, Homebrew or npm, as listed in the README badges
- Read the documentation and tutorials
- Convert a model from PyTorch, TensorFlow, ONNX or another supported framework
- Run inference on your target CPU, GPU or NPU
Models & InferenceIntermediate
910Python+1/daypushed 7d ago
Use it for: Explore use cases, patterns, prompts and starter code for TypeSafe Jev, a model for fast, typed, confidence-aware software decisions.
Quick start
- Open the repo and browse the use cases and patterns
- Pick a pattern that matches your task, such as classification or routing
- Copy the starter code or prompts into your project
- Clone the repo and follow any setup notes included in the files
