Original model: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
Tested on Snapdragon X Elite with LM Studio 0.3.2 ARM64 Technology Preview https://lmstudio.ai/snapdragon
Avg answer Speed: 30 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
- Downloads last month
- 34
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for pipilok/Llama-3.2-3B-Instruct-Q4_0_4_8-GGUF
Base model
meta-llama/Llama-3.2-3B-Instruct