quantprobe
High-performance LLM quantization and inference tool optimized for low memory usage and high token speed.
Why it made the shelf
The submitted repository is a developer tool and library designed to run large language models efficiently with low.
Seen on
- First seen
- 2 months ago
- Best score
- 5 points
Behind the tool
Who built it. How it grew.
People, backing, growth, and ownership. Every claim links to its source.
Official sitegithub.com
Source review queued
Public trail
Where it showed up
2 references from 1 publisher.
- First trace
- Hacker News2 months ago
- Strongest thread
- Hacker News5 points
- 01Hacker NewsStrongest discussion
I run 30B 22tok/s, 109tok/s not novel,6GB/16GB RAM overcoming llama.cpp
- 02
