A GGUF Q4_K_M quantization of emre/gemma-3-27b-it-tr-reasoning40k-4bit for ultra-fast, low-RAM local inference with llama.cpp (and compatible back-ends).

No weights were changed beyond quantization; alignment, vocabulary and tokenizer remain intact.

Developed by: emre
Finetuned from model : unsloth/gemma-3-27b-it-unsloth-bnb-4bit

This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Tiotanio/gemma-3-27b-it-tr-reasoning_Q4_K_M

Gemma-3-27B-it-tr-reasoning · Q4_K_M (GGUF)

Tiotanio/
gemma-3-27b-it-tr-reasoning_Q4_K_M