HF Quantization

community

AI & ML interests

Making AI models smaller, and faster with Quantization

Collections 1

spaces 3

TorchAO

Quantize and upload Hugging Face models

Running on A10G

BitsAndBytes

Quantize and save models to Hugging Face

TorchAO

Quantize Hugging Face models and save to your profile

models 11

HF-Quantization/Llama-3.3-70B-Instruct-TORCHAO-W8

HF-Quantization/Llama-3.3-70B-Instruct-TORCHAO-W4

Updated Jan 22 • 4

HF-Quantization/Llama-3.2-1B-BNB-INT8

1B • Updated Jan 21 • 5

HF-Quantization/Llama-3.2-1B-BNB-NF4

0.8B • Updated Jan 21 • 3

HF-Quantization/Llama-3.2-1B-BNB-FP4

0.8B • Updated Jan 21 • 19

HF-Quantization/Llama-3.2-1B-BNB-NF4-BF16

0.8B • Updated Jan 21 • 26

HF-Quantization/Llama-3.2-1B-BNB-FP4-BF16

0.8B • Updated Jan 21 • 6

HF-Quantization/Llama-3.2-1B-TORCHAO-W8A8

Updated Jan 21 • 29

HF-Quantization/Llama-3.2-1B-TORCHAO-W8

Updated Jan 21 • 2

HF-Quantization/Llama-3.2-1B-TORCHAO-W4

Updated Jan 21 • 4

datasets 0

None public yet