# Llama2 response times - feedback **URL:** \ **Category:** Beginners\ **Created:** [February 6, 2024, 2:43am UTC](https://discuss.huggingface.co/t/llama2-response-times-feedback/72011 "2024-02-06T02:43:13Z")\ **Posts on this page:** 1\ **Page:** 1
**Author:** ![VeeP](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/veep/32/20911_2.png) [@VeeP](https://discuss.huggingface.co/u/VeeP)\ **Post date:** [February 6, 2024, 2:43am UTC](https://discuss.huggingface.co/t/llama2-response-times-feedback/72011/1 "2024-02-06T02:43:13Z")
Hello, I am trying out the meta-llama/Llama-2-13b-chat-hf on a local system Nvidia 4090 (24GB vram) 64 GB ram i9-13900KF Enough disk space. pretty much doing this: # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from\_pretrained(“meta-llama/Llama-2-13b-chat-hf”) model = AutoModelForCausalLM.from\_pretrained(“meta-llama/Llama-2-13b-chat-hf”) (file installed locally( When I give it a prompt, here are the times: **Using device: cuda** **huggingface\hub** **Model loaded successfully in 239.82 seconds.** **Enter your prompt: What will climate change be like in 30 years from today** **Prompt received.** **Encoding prompt…** **Generating response…** **Response generated in 924.54 seconds.** **Decoding response…** Response: What will climate change be like in 30 years from today? (example prompt. Darth Vader question took longer) Climate change is one of the most pressing issues of our time, and its impacts will only continue to grow more severe as the years go by. Here are some potential effects of climate change that we may see in the next 30 years:…(clipped) . **Logging GPU usage…** **Memory Allocated: 26124154880** **Memory Cached: 52818870272** It has gone as high as 1500+ seconds (25 minutes). Is anyone else getting durations like this on a local setup? I have not tried the 7b chat yet. Just curious! Thanks, V