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
... /
template
5f26a434dfac · 266B
{{ if .System }}<start_of_turn>user
{{ .System }}<end_of_turn>
{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<start_of_turn>user
{{ .Content }}<end_of_turn>
<start_of_turn>model
{{ else if eq .Role "assistant" }}{{ .Content }}<end_of_turn>
{{ end }}{{ end }}