Q4_K_M
The conversion repository lists google_gemma-4-31B-it-Q4_K_M.gguf at 19.60 GB; its rounded decimal file size is converted to GiB for planning. This does not include context or runtime memory.
- Bits per weight
- 4.5
- Model size
- 18.25 GiB
Model catalog
Gemma 4 31B IT
Google's dense multimodal instruction model. Listed GGUF sizing covers the main model weights; the separate vision projector is excluded.
Model overview
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.
Compatibility notes
Estimates use the cataloged model-weight size (or a parameter-based estimate), apply weight overhead, and include standard runtime overhead. They do not include context/KV-cache memory. Real requirements vary with runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.
Google Gemma 4 31B IT model card; verified value, last verified 2026-09-29. Google identifies the 31B dense multimodal instruction model, Apache-2.0 licensing, and up to 256K context. GGUF weight sizing and the separate vision projector are sourced independently from the conversion repository. View source
Multimodal memory scope: This estimate excludes the separate vision/projector file and its runtime memory. bartowski Gemma 4 31B IT GGUF repository