edgenai/edgen
⚡ Edgen: Local, private GenAI server alternative to OpenAI. No GPU required. Run AI models locally: LLMs (Llama2, Mistral, Mixtral...), Speech-to-text (whisper) and many others.
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
Appears on
Quick read
Latest capture 2026-09-08 10:55
11 paths
Agent instructions and tool configuration found in this repository.
1 observed capture since 2026-09-08. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
⚡ Edgen: Local, private GenAI server alternative to OpenAI. No GPU required. Run AI models locally: LLMs (Llama2, Mistral, Mixtral...), Speech-to-text (whisper) and many others.
🏗️ Fine-tune, build, and deploy open-source LLMs easily!
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.
LLM speculative inference server for heterogeneous hardware & consumer GPUs
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
Qwen3.8 is the large language model series developed by Qwen team, Alibaba Group.