GF

GPTQ-for-LLaMa

Model Optimization·infrastructure·open·#813 of 886·+87·Stable·Breakout #3

57.8

Low

High confidence
GitHub

4 bits quantization of LLaMA using GPTQ

Pillar Breakdown

Adoption

35%

46.7

Maintenance

30%

61.9

Friction

20%

96.2

Ecosystem

15%

38.5

Momentum

0.43Stable
7d change -0.53
High confidence

In Model Optimization

Ranked #16 of 17

1onnx
87.9
2Safetensors
83.8
3bitsandbytes
83.2
4ONNX Runtime
82.6
5DeepSpeed
78.4
6TensorRT
76.0
7Optimum
75.8
8numba
75.1
See all 17 in Model Optimization →

Similar Tools

AU

AutoAWQ

Model Optimization

57.9

OQ

optimum-quanto

Model Optimization

58.3

BI

BitBLAS

Model Optimization

56.3

LL

lit-llama

Model Optimization

59.6