FreeAIRepo
Inference & serving

ARahim3/kaggle-tpu-lab

Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code,

Really freeMITPython
Stars
704
Forks
95
Open issues
13
Last push
16d ago

About kaggle-tpu-lab

kaggle-tpu-lab is a free, open-source AI inference tool by ARahim3, written mainly in Python. Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code,. It has 704 GitHub stars and 95 forks, and was last updated 16d ago. It's released under the MIT license, a standard open-source license.

License
MIT
Language
Python
Stars
704
Last update
16d ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not required
Self-hostable
Not stated

Similar free tools

All Inference & serving tools →

kaggle-tpu-lab FAQ

Is kaggle-tpu-lab free?

Yes. kaggle-tpu-lab is open source and free to use. It's released under the MIT license, a standard open-source license.

Does kaggle-tpu-lab run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does kaggle-tpu-lab need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is kaggle-tpu-lab still maintained?

Yes. It was last updated 16d ago and has 13 open issues on GitHub.

What are alternatives to kaggle-tpu-lab?

Similar free, open-source tools include vllm, llm-action, TensorRT-LLM, inference.

Related topics