Upload README.md with huggingface_hub

README.md

@@ -44,8 +44,11 @@ This model is an implementation of Llama-v3.1-8B-Chat found [here](https://githu
   - TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (4096 tokens).
   - Response Rate: Rate of response generation after the first response token.
 
-| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
-|---|---|---|---|---|---|---|---|---|
+| Model | Precision | Device | Chipset | Target Runtime | Response Rate (tokens per second) | Time To First Token (range, seconds)
+|---|---|---|---|---|---|
+| Llama-v3.1-8B-Chat | w4a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 13.0546 | 0.154517 - 4.944544 | -- | -- |
+| Llama-v3.1-8B-Chat | w4a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 9.357 | 0.207727 - 6.647264 | -- | -- |
+| Llama-v3.1-8B-Chat | w4a16 | SA8255P ADP | Qualcomm® SA8255P | QNN | 7.93185 | 0.3297069 - 10.5506208 | -- | -- |
 
 ## Deploying Llama 3.1 on-device