GF

GPTQ-for-LLaMa

Model Optimization·infrastructure·open·#821 of 944·-122·Falling·Breakout #3

60.1

Low

High confidence
GitHub

4 bits quantization of LLaMA using GPTQ

Pillar Breakdown

Adoption

35%

51.3

Maintenance

30%

62.9

Friction

20%

98.5

Ecosystem

15%

38.5

Momentum

0.06Falling
7d change -4.66
High confidence

In Model Optimization

Ranked #13 of 16

1onnx
87.2
2Safetensors
84.1
3bitsandbytes
82.8
4ONNX Runtime
81.4
5DeepSpeed
78.0
6Optimum
77.4
7TensorRT
76.8
8neural-compressor
70.7
See all 16 in Model Optimization →

Similar Tools

AU

AutoAWQ

Model Optimization

59.9

OQ

optimum-quanto

Model Optimization

63.7

LA

llm-awq

Model Optimization

55.9

LT

lightly-train

Model Optimization

66.3