Original model: https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat
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
- 56
Model tree for pipilok/DeepSeek-V2-Lite-Chat-Q4_0_4_8-GGUF
Base model
deepseek-ai/DeepSeek-V2-Lite-Chat