These are quantizations of the model openPangu-Embedded-7B-DeepDiver

Original model: https://huggingface.co/FreedomIntelligence/openPangu-Embedded-7B-DeepDiver

Download the latest llama.cpp to use them.

Downloads last month
27
GGUF
Model size
8B params
Architecture
pangu-embedded
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for noctrex/openPangu-Embedded-7B-DeepDiver-GGUF

Quantized
(3)
this model