Hugging Face's logo

litert-community
/
gemma-4-E2B-it-litert-lm

LiteRT-LM
Model card Files
xet
 Community
33
marissaw commited on
Commit
753814e
·
verified ·
1 Parent(s): f85d401

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -28,6 +28,8 @@ All benchmarks were taken using 1024 prefill tokens and 256 decode tokens with a
28
 
29
  CPU memory was measured using, rusage::ru_maxrss on Android, Linux and Raspberry Pi, task_vm_info::phys_footprint on iOS and MacBook and process_memory_counters::PrivateUsage on Windows.
30
 
 
 
31
  **Android**
32
 
33
  *Note: On [supported Android devices](https://developers.google.com/ml-kit), Gemma 4 is available through Android AI Core as [Gemini Nano](https://developer.android.com/ai/gemini-nano#architecture), which is the recommended path for production applications.*
 
28
 
29
  CPU memory was measured using, rusage::ru_maxrss on Android, Linux and Raspberry Pi, task_vm_info::phys_footprint on iOS and MacBook and process_memory_counters::PrivateUsage on Windows.
30
 
31
+ We use the Gemma quantization scheme that employs a mixture of 2bit, 4bit and 8bit weights.
32
+
33
  **Android**
34
 
35
  *Note: On [supported Android devices](https://developers.google.com/ml-kit), Gemma 4 is available through Android AI Core as [Gemini Nano](https://developer.android.com/ai/gemini-nano#architecture), which is the recommended path for production applications.*