4-bit OmniQuant quantized version of Dolphin3.0-Llama3.2-1B for inference with Private LLM.
- Downloads last month
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for numen-tech/Dolphin3.0-Llama3.2-1B-w4a16g128asym
Base model
meta-llama/Llama-3.2-1B