# Can I run Gemma 3 12B on Nvidia GeForce RTX 4080 (16GB)?

> **Yes, it runs.** Runs at Q4_K_M using ~8.9 GB of ~15 GB usable. You have room for Q8_0 for higher quality.

Last validated: 2026-06-15.

## Memory math
- Gemma 3 12B: 12B; Q4_K_M weighs 7.3 GB on disk.
- At Q4_K_M with a 4k context it needs ~8.9 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- Nvidia GeForce RTX 4080 (16GB): 16 GB vram, ~15 GB usable for model weights.
- Headroom: ~6.1 GB; it also fits Q8_0 for higher quality.

## How to run
Recommended quant: Q4_K_M. Best tool on Windows: LM Studio.

```sh
ollama run gemma3:12b
```

## Run Gemma 3 12B on other devices
- [Nvidia GeForce RTX 3060 (12GB)](https://localmodel.run/can-i-run/gemma-3-12b/nvidia-rtx-3060-12gb)
- [Nvidia GeForce RTX 4070 (12GB)](https://localmodel.run/can-i-run/gemma-3-12b/nvidia-rtx-4070-12gb)
- [Apple M2 (16GB)](https://localmodel.run/can-i-run/gemma-3-12b/apple-m2-16gb)
- [Apple M4 (16GB)](https://localmodel.run/can-i-run/gemma-3-12b/apple-m4-16gb)
- [Nvidia GeForce RTX 4060 Ti (16GB)](https://localmodel.run/can-i-run/gemma-3-12b/nvidia-rtx-4060-ti-16gb)
- [16GB RAM Laptop (CPU/iGPU only)](https://localmodel.run/can-i-run/gemma-3-12b/laptop-16gb)

## Other models that run on Nvidia GeForce RTX 4080 (16GB)
- [gpt-oss 20B (21B)](https://localmodel.run/can-i-run/gpt-oss-20b/nvidia-rtx-4080-16gb)
- [DeepSeek-V2-Lite (16B)](https://localmodel.run/can-i-run/deepseek-v2-lite/nvidia-rtx-4080-16gb)
- [Phi-4 14B (14B)](https://localmodel.run/can-i-run/phi-4-14b/nvidia-rtx-4080-16gb)
- [Qwen2.5 14B (14B)](https://localmodel.run/can-i-run/qwen2.5-14b/nvidia-rtx-4080-16gb)
- [Qwen3 14B (14B)](https://localmodel.run/can-i-run/qwen3-14b/nvidia-rtx-4080-16gb)
- [DeepSeek-R1-Distill-Qwen 14B (14B)](https://localmodel.run/can-i-run/deepseek-r1-distill-qwen-14b/nvidia-rtx-4080-16gb)

Estimate, not a guarantee. Sources: https://ollama.com/library/gemma3, https://ollama.com/library/gemma3/tags, https://huggingface.co/bartowski/google_gemma-3-12b-it-GGUF, https://lmarena.ai/leaderboard.
More: https://localmodel.run/can-i-run/gemma-3-12b/nvidia-rtx-4080-16gb