numen-tech
/

Dolphin3.0-Llama3.2-3B-w4a16g128asym

Text Generation

4-bit precision

Model card Files Files and versions

4-bit OmniQuant quantized version of Dolphin3.0-Llama3.2-3B for inference with Private LLM.

Downloads last month: -

Model tree for numen-tech/Dolphin3.0-Llama3.2-3B-w4a16g128asym

Base model

meta-llama/Llama-3.2-3B

Finetuned

dphn/Dolphin3.0-Llama3.2-3B

Quantized

(28)

this model