metadata
license: llama3.2
quantized_by: pipilok
pipeline_tag: text-generation
base_model:
- meta-llama/Llama-3.2-1B-Instruct
Original model: https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct
Tested on Snapdragon X Elite with LM Studio 0.3.2 ARM64 Technology Preview https://lmstudio.ai/snapdragon
Avg answer Speed: 60 tok/s
LM Studio Settings:
Before System: <|im_start|>system\n
After System: <|im_end|>\n
Before User: <|im_start|>user\n
After User: <|im_end|>\n
Before Assistant: <|im_start|>assistant\n
After Assistant: <|im_end|>\n