gemma-4-12b-it-GGUF
- Home
- / Recommended Models
- / gemma-4-12b-it-GGUF
gemma-4-12b-it-GGUF
VRAM needed
≈ 16 GB
Fits 16 GB+ consumer GPUs
Authorunsloth
Parameters12B
QuantizationQ4_K_M
FormatGGUF
Licenseapache-2.0
File size6.63 GB
Overview
Gemma 4 12B instruction-tuned - strong reasoning and tool-calling for its size. Excellent quality-per-GB fit for 16 GB cards.
Recommended hardware
≈ 16 GB VRAM to run this 12B model at the Q4_K_M quantization.
Fits 16 GB+ consumer GPUs (e.g. RTX 4060 Ti 16GB, RTX 4080)