# Can I run Gemma 2 2B on Nvidia GeForce RTX 4090 (24GB)?

> **Yes, it runs.** Runs at Q4_K_M using ~2.9 GB of ~23 GB usable. You have room for FP16 for higher quality.

Last validated: 2026-06-15.

## Memory math
- Gemma 2 2B: 2.61B; Q4_K_M weighs 1.71 GB on disk.
- At Q4_K_M with a 4k context it needs ~2.9 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- Nvidia GeForce RTX 4090 (24GB): 24 GB vram, ~23 GB usable for model weights.
- Headroom: ~20.1 GB; it also fits FP16 for higher quality.

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

```sh
ollama run gemma2:2b
```

## Run Gemma 2 2B on other devices
- [Apple M1 (8GB)](https://localmodel.run/can-i-run/gemma-2-2b/apple-m1-8gb)
- [8GB RAM Laptop (CPU/iGPU only)](https://localmodel.run/can-i-run/gemma-2-2b/laptop-8gb)
- [iPhone 15 Pro](https://localmodel.run/can-i-run/gemma-2-2b/iphone-15-pro)
- [iPhone 16](https://localmodel.run/can-i-run/gemma-2-2b/iphone-16)
- [iPhone 16 Pro](https://localmodel.run/can-i-run/gemma-2-2b/iphone-16-pro)
- [Generic Android Phone (8GB RAM)](https://localmodel.run/can-i-run/gemma-2-2b/android-generic-8gb)

## Other models that run on Nvidia GeForce RTX 4090 (24GB)
- [Command R 35B (35B)](https://localmodel.run/can-i-run/command-r-35b/nvidia-rtx-4090-24gb)
- [Yi 1.5 34B (34B)](https://localmodel.run/can-i-run/yi-1.5-34b/nvidia-rtx-4090-24gb)
- [Qwen2.5 32B (32B)](https://localmodel.run/can-i-run/qwen2.5-32b/nvidia-rtx-4090-24gb)
- [Qwen3 32B (32B)](https://localmodel.run/can-i-run/qwen3-32b/nvidia-rtx-4090-24gb)
- [DeepSeek-R1-Distill-Qwen 32B (32B)](https://localmodel.run/can-i-run/deepseek-r1-distill-qwen-32b/nvidia-rtx-4090-24gb)
- [Qwen2.5 Coder 32B (32B)](https://localmodel.run/can-i-run/qwen2.5-coder-32b/nvidia-rtx-4090-24gb)

Estimate, not a guarantee. Sources: https://ollama.com/library/gemma2:2b, https://huggingface.co/bartowski/gemma-2-2b-it-GGUF, https://huggingface.co/blog/gemma-july-update, https://huggingface.co/blog/gemma2.
More: https://localmodel.run/can-i-run/gemma-2-2b/nvidia-rtx-4090-24gb