aravhawk/ gemma4:26b-a4b-it-q3_k_s

545 1 week ago

Gemma 4 26B Optimized for 16GB VRAM via Q3 Quantization

tools thinking 26b
... /
params
9ec961080a53 · 132B
{
"num_ctx": 100000,
"num_gpu": 99,
"repeat_penalty": 1,
"stop": [
"<end_of_turn>",
"<start_of_turn>"
],
"temperature": 0.7
}