text model · gemma · Windows
Can I run Gemma 3 12B on Nvidia GeForce RTX 4090 (24GB)?
Yes. Gemma 3 12B runs on Nvidia GeForce RTX 4090 (24GB) at Q4_K_M (~8.9 GB of ~23 GB usable).
Runs at Q4_K_M using ~8.9 GB of ~23 GB usable. You have room for Q8_0 for higher quality.
- Q4_K_M needed
- ~8.9 GB
- Usable on device
- ~23 GB
- Device memory
- 24 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run gemma3:12b llama-cli -hf bartowski/google_gemma-3-12b-it-GGUF:Q4_K_M lms get bartowski/google_gemma-3-12b-it-GGUF AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
- Parameters
- 12B
- Q4_K_M size
- 7.3 GB
- Q8_0 size
- 12.51 GB
- Context
- 128k
- Ollama tag
- gemma3:12b
- Memory
- 24 GB vram
- Usable for weights
- ~23 GB
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
You could also run
Run Gemma 3 12B on other hardware
FAQ
Can Nvidia GeForce RTX 4090 (24GB) run Gemma 3 12B?
Yes. Gemma 3 12B runs on Nvidia GeForce RTX 4090 (24GB) at Q4_K_M (~8.9 GB of ~23 GB usable).
How much memory does Gemma 3 12B need?
Nvidia GeForce RTX 4090 (24GB) has room to spare. At Q4_K_M the weights are ~7.3 GB; with KV cache and runtime overhead, budget ~8.9 GB at a 4k context.
What is the best tool to run Gemma 3 12B on Windows?
LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
Sources
Memory figures are estimates. See methodology.