File size: 510 Bytes
f8bc745 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 |
---
license: llama3.2
quantized_by: pipilok
pipeline_tag: text-generation
---
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
```
|