Update README.md

README.md

@@ -81,11 +81,21 @@ It uses the Gemma quantization scheme that employs a mixture of 2bit, 4bit and 8
 | Device &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;| Backend | Prefill (tokens/sec) | Decode (tokens/sec) | <span style="white-space: nowrap;">Time-to-first</span>-token (sec) | Model size (MB) | CPU Memory (MB) |
 | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
 | Raspberry Pi 5 16GB | CPU | 133 | 7.6 | 7.8 | 2583 | 1546 |
-| Qualcomm IQ-8275 EVK | NPU* | 2371 | 18.8 | 0.5 | 2688 | 1471 |
+| Qualcomm IQ-8275 EVK | NPU* | 2,371 | 18.8 | 0.5 | 2688 | 1471 |
 
 \* NPU model is benchmarked with 4096 context length
 
 
 ## Gemma 4 E2B Performance on Web
 
+Running Gemma inference on the web is currently supported through [LLM Inference Engine](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference/web_js) and uses the *gemma-4-E2B-it-web.task* model file. To try it out, download [the web model](https://huggingface.co/litert-community/gemma-4-E2B-it-litert-lm/blob/main/gemma-4-E2B-it-web.task) and run with our [sample web page](https://github.com/google-ai-edge/mediapipe-samples/blob/main/examples/llm_inference/js/README.md), or follow the [guide](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference/web_js) to add it to your own app.
 
+Benchmarked in Chrome on a MacBook Pro 2024 (Apple M4 Max) with 1024 prefill tokens and 256 decode tokens, but the model can support context lengths up to 128K.
+
+| Device | Backend | Prefill (tokens/sec) | Decode (tokens/sec) | <span style="white-space: nowrap;">Time-to-first</span>-token (sec) | Model size (MB) | CPU Memory (MB) | GPU Memory (MB) |
+| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
+| Web | GPU | 4,676 | 73.9 | 1.1 | 1.5 | 1546 | 1.8 |
+
+<small>\* GPU memory measured by "GPU Process" memory for all of Chrome while running. Was 130MB when inactive, before any model loading took place.
+
+\* CPU memory measured for the entire tab while running. Was 55MB when inactive, before any model loading took place.<small>