OnlyTerp/turboquant
First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.
- Stars
- 85
- Forks
- 12
- Open issues
- 0
- Last push
- 5mo ago
turboquant star history
+0 this week
About turboquant
turboquant is a free, open-source AI inference tool by OnlyTerp, written mainly in Python. First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss. It has 85 GitHub stars and 12 forks, and was last updated 5mo ago. It's released under the MIT license, a standard open-source license. According to the project, it works on macOS.
- License
- MIT
- Commercial use
- Commercial OK
- Language
- Python
- Stars
- 85
- Last update
- 5mo ago
- Runs on Mac
- Yes (as stated by the project)
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Not stated
Similar free tools
DeepSpeed43k stars · DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
vllm95k stars · High-throughput inference engine for LLMs.
ray44k stars · Distributed AI compute engine for ML and RL workloads.
llm-action25k stars · 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
nano-vllm16k stars · A fast, lightweight inference engine for language models.
LMCache12k stars · Accelerates LLM inference by managing KV cache.
turboquant FAQ
Can I use turboquant commercially?
Yes. MIT is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.
Is turboquant free?
Yes. turboquant is open source and free to use. It's released under the MIT license, a standard open-source license.
Does turboquant run on a Mac?
Yes. According to the project, turboquant works on macOS.
Does turboquant need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is turboquant still maintained?
It was last updated 5mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to turboquant?
Similar free, open-source tools include DeepSpeed, vllm, ray, llm-action.
Maintain turboquant?
Add this badge to your README to show it's featured on FreeAIRepo.
[](https://www.freeairepo.com/repo/OnlyTerp/turboquant)