GreenBit LLMs

This is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.

Please refer to our Github page for the code to run the model and more information.

Safetensors

Model size

2.15B params

Tensor type

FP16

I32

I16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Collection including GreenBitAI/Qwen-1.5-7B-layer-mix-bpw-4.0