Gemma 4 12B — 11.96B Dense.
Run Gemma 4 12B locally with Ollama — needs 7.8 GB VRAM at Q4_K_M:
ollama run gemma4:12b| Quant | Bits | VRAM @ 16K | Quality |
|---|---|---|---|
| Q3_K_M | 4 | 7.0 GB 6.5 + 0.5 KV | low |
| Q3_K_L | 4.3 | 7.4 GB 6.9 + 0.5 KV | moderate |
| IQ4_XS | 4.46 | 7.7 GB 7.2 + 0.5 KV | moderate |
| Q4_K_S | 4.67 | 8.0 GB 7.5 + 0.5 KV | moderate |
| Q4_K_M | 4.89 | 8.3 GB 7.8 + 0.5 KV | good |
| Q5_K_S | 5.57 | 9.3 GB 8.8 + 0.5 KV | good |
| Q5_K_M | 5.7 | 9.5 GB 9.0 + 0.5 KV | good |
| Q6_K | 6.56 | 10.8 GB 10.3 + 0.5 KV | excellent |
| Q8_0 | 8.5 | 13.7 GB 13.2 + 0.5 KV | lossless |
| FP16 | 16 | 24.9 GB 24.4 + 0.5 KV | lossless |
Select your GPU above to see speed estimates and compatibility for each quantization.
Rent a GPU and run Gemma 4 12B now
Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.
Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.
At Q4_K_M quantization. Sorted by minimum VRAM.
Find the best GPU for Gemma 4 12B
Build Hardware for Gemma 4 12BRun Gemma 4 12B locally with Ollama — needs 7.8 GB VRAM at Q4_K_M:
ollama run gemma4:12b