# Gemma 4 12B: RAM and VRAM requirements

> Gemma 4 12B is a 12B Gemma model. At Q4_K_M it needs about **8.7 GB** to run and fits **29 of 40** tracked devices. Minimum to run: Nvidia GeForce RTX 3060 (12GB).

Last validated: 2026-08-03. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 7.12 GB | ~8.7 GB |
| Q8_0 | 12.67 GB | ~14.3 GB |
| FP16 | 23.83 GB | ~25.4 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Apple M1 (8GB)** (8 GB): No, not enough memory
- **iPhone 17** (8 GB): No, not enough memory
- **iPhone 17 Pro** (12 GB): No, not enough memory
- **16GB RAM Laptop (CPU/iGPU only)** (16 GB): Yes, it runs
- **Google Pixel 10 Pro** (16 GB): Yes, it runs
- **Nvidia GeForce RTX 3090 (24GB)** (24 GB): Yes, it runs (room for Q8_0)
- **Apple M4 Pro (48GB)** (48 GB): Yes, it runs (room for FP16)
- **Apple M3 Ultra (256GB)** (256 GB): Yes, it runs (room for FP16)

Full table of all 40 devices: https://localmodel.run/model/gemma-4-12b

## How to run
Quickest path: `ollama run gemma4:12b`. On Mac, LM Studio (ships MLX) is fastest; on Linux, Ollama for chat or vLLM to serve; on Windows, LM Studio or Ollama.

## Details
- Parameters: 12B
- Default context: 256k tokens
- License: Apache-2.0 (commercial use: yes)
- Released: 2026-05
- HuggingFace: 3,028,659 downloads/mo, 1390 likes

## FAQ
### How much VRAM or RAM does Gemma 4 12B need?
About 8.7 GB at Q4_K_M (weights 7.12 GB + KV cache + overhead) at a 4k context. Budget ~14.3 GB for Q8_0.
### Can Gemma 4 12B run on a laptop?
Gemma 4 12B is large; you need a high-memory Mac or a 24 GB+ GPU at Q4_K_M.
### Can I use Gemma 4 12B commercially?
Yes, Apache-2.0 permits commercial use.

Sources: https://huggingface.co/google/gemma-4-12B-it, https://huggingface.co/unsloth/gemma-4-12B-it-GGUF, https://ollama.com/library/gemma4/tags
More: https://localmodel.run/model/gemma-4-12b