edtorre/ gemma4-26b-a4b-it-qat-agent:latest

52 4 days ago

Gemma 4 26B tuned for agentic use. 64K context window, flash attention + Q8 KV cache quantization for reduced VRAM. Temperature 0.7, output capped at 8192 tokens.

vision tools thinking
... /
params
f5434592278f · 79B
{
"num_ctx": 65536,
"num_predict": 4096,
"temperature": 0.7,
"top_k": 64,
"top_p": 0.95
}