4skl/ gemma4-e2b-mtp:latest

27 yesterday

Ultra-fast 2.3B Gemma 4 model for on-device edge AI (2.7GB). Combines Unsloth Dynamic QAT with a low-latency 2-token MTP pipeline and a mobile-safe 32K context window. Perfect for smartphones and laptops sharing 8GB of total system RAM.

tools thinking
... /
params
205796ff7d83 · 87B
{
"draft_num_predict": 2,
"num_ctx": 32768,
"stop": [
"<turn|>"
],
"temperature": 0.4
}