S
T
A
R
N
G
A
G
E
About
GGML is a tensor library for machine learning to enable large models and high performance on commodity hardware.
Website Rank
1.95M
1.95M
Category Rank
(Computers_Elect…) 23.8K
(Computers_Elect…) 23.8K
Country Rank
(US) 1.71M
(US) 1.71M
Website Traffic
35.7K
35.7K
Monthly Visits Trend
Top Traffic Countries
Top Traffic Sources
Recent Reviews
-
-
Company Size
-
-
Employees On Linkedin
-
-
Twitter Followers
Twitter Likes
Twitter Posts
Facebook Followers
-
-
Facebook Likes
-
-
Summary
GGML is a tensor library for machine learning designed to enable large models and high performance on commodity hardware.
Features
- Enables large models and high performance on commodity hardware
- Used by llama.cpp and whisper.cpp
- Provides high-quality speech-to-text solution
- Demonstrates efficient inference on Apple Silicon hardware
- Open source with MIT license
- Encourages contributors to try creative ideas and push the boundaries of what's possible
Use Cases
- Short voice command detection on a Raspberry Pi 4
- Simultaneously running multiple instances of models on a single device
- Running large language models at high throughput
- High-performance inference of automatic speech recognition
- Efficient inference on Apple Silicon hardware
- Optimization techniques and applications of large language models
