GradientHQ/parallax
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
Setting up and managing large AI models (like ChatGPT, Llama) on your own servers or devices can be complex and expensive. Parallax simplifies this by letting you pool your existing computing power, even across different machines and locations, to run these models efficiently. It takes your chosen large language model and helps you deliver its predictions or responses to users without needing specialized, costly infrastructure. This is designed for organizations and individuals who want to host powerful AI models themselves, without relying on external cloud providers.
1,152 stars. Actively maintained with 2 commits in the last 30 days.
Use this if you need to run large AI models on your own hardware, distributing the workload across multiple machines for cost-effectiveness and control.
Not ideal if you prefer to use fully managed cloud services for your AI model hosting or only need to run small, less resource-intensive models.
Stars
1,152
Forks
118
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/GradientHQ/parallax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
shibing624/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline....
lyogavin/airllm
AirLLM 70B inference with single 4GB GPU
CrazyBoyM/llama3-Chinese-chat
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。
CLUEbenchmark/CLUE
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained...
MediaBrain-SJTU/MING
明医 (MING)：中文医疗问诊大模型