unsloth

/

gemma-4-26B-A4B-it-GGUF

like 577

Follow

Unsloth AI 19.7k

Hi,
thanks for keeping the GGUFs up to date. How to properly set the visual token budget [0] in llama.cpp server cli or api requests?
Appart from that, is using --jinja not needed anymore? (asking because you do not use it in your examples)

[0] https://unsloth.ai/docs/models/gemma-4#ocr-document-prompt