4skl/ gemma4-e4b-mtp:latest

42 yesterday

Optimized 4.5B Gemma 4 model with Unsloth Dynamic QAT & MTP (4.3GB). Features near-lossless multimodal reasoning, an active 4-token speculative window, and an expanded 64K context size. Best for edge execution on systems with 8GB to 16GB RAM.

tools thinking
... /
params
780eb2d4f8f6 · 87B
{
"draft_num_predict": 4,
"num_ctx": 65536,
"stop": [
"<turn|>"
],
"temperature": 0.6
}