Skip to main content

CSGLite Introduction

CSGLite is a lightweight tool for running large language models locally, powered by models from the CSGHub platform.

Inspired by Ollama, csghub-lite provides model download, local inference, interactive chat, and an OpenAI-compatible REST API — all from a single binary.

Features​

  • One command to start — csghub-lite run downloads, loads, and chats.
  • Model keep-alive — models stay loaded in memory after exit (default 5 min) for instant reconnect.
  • Auto-start server — background API server starts automatically, no manual setup.
  • Model download from the CSGHub platform (hub.opencsg.com or private deployments).
  • Local inference via llama.cpp (GGUF models, SafeTensors auto-converted).
  • Interactive chat with streaming output.
  • REST API compatible with Ollama and OpenAI's API format.
  • Cross-platform — macOS, Linux, Windows.
  • Resume downloads — interrupted downloads resume where they left off.
  • Pause/Resume — pause ongoing downloads and resume later.
  • Web UI:
    • Dashboard: Monitor resources (CPU, RAM, VRAM) and manage running models/live logs.
    • Marketplace: Browse and download models/datasets from CSGHub with one click.
    • Model Library: Manage local models with download progress, pause/resume, and one-click run.
    • Chat Interface: Stream-based chat with local and cloud models, featuring temperature, top-p, context length tuning, and system prompt setup.
    • AI Apps: Install and launch AI applications (e.g., Claude Code, Codex, OpenClaw, Dify) with one-click configuration.
    • Settings: Configure storage paths, context windows, interface language (CN/EN), and view versions.
  • Third-Party Providers — Integrate OpenAI, DeepSeek, MiMo, Kimi, BigModel, Qianfan, MiniMax, OpenRouter, and any OpenAI-compatible API.
  • Dataset Support — Download, list, view details, and manage local datasets from CSGHub.

Model Formats​

FormatDownloadInference
GGUFYesYes (via llama.cpp)
SafeTensorsYesYes (auto-converted to GGUF)

SafeTensors checkpoints are converted once using the bundled llama.cpp convert_hf_to_gguf.py and system Python (PyTorch is not shipped inside the release binary). Install these packages once:

pip3 install torch safetensors gguf transformers

Use Python 3.10+ on PATH (Windows: python or python3). Some models may need extra packages (for example sentencepiece); see convert instruction for the full list and troubleshooting (gguf version mismatch, optional CSGHUB_LITE_CONVERTER_URL).