Model catalog

Gemma 3 12B IT

The 12B Gemma 3 instruction model adds a larger text-and-image family option; this estimate covers text weights only.

Check this model on your hardware See what your PC can run

Model overview

Family: Gemma 3
Provider: Google
Architecture: Gemma
Parameters: 12B
Formats: gguf, safetensors
Runtimes: llama.cpp
License: Gemma Terms of Use
Maximum context: 131,072 tokens

Available quantizations

Lower-bit quantizations generally use less memory. The compatibility calculator uses these candidates and its transparent approximate memory assumptions; it does not make a performance guarantee.

Q4_K_M

A commonly available lower-memory GGUF variant; the listed memory input is an estimate, not the repository file size.

Bits per weight: 4.5
Source: ggml-org/gemma-3-12b-it-GGUF GGUF repository

Compatibility notes

Weight estimates are approximate and include a runtime overhead. Real requirements vary with context length, runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.

Google Gemma 3 12B IT model card; verified value, last verified 2026-09-23. Publisher metadata; image encoder, image tokens, and multimodal runtime memory are not modeled. The ggml-org repository provides a separate GGUF conversion. View source