Gemma 3 12B on NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 runs Gemma 3 12B excellently at 75 tok/s at Q5_K_M. This is a strong pairing.
Model Size
12.2B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Gemma 3 12B performance at a different quality level on NVIDIA GeForce RTX 4090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 75 tok/s | 95ms | ✓ Yes | Excellent | estimated |
Notes
Q5_K_M
Excellent speed at Q5. Fast inference for 12B class.
About Gemma 3 12B
Gemma 3 12B (12.2B) is a chat, coding, multi-purpose model. Google's efficient 12B model with strong chat and coding support.
View all Gemma 3 12B hardware options →About NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Source: Community benchmarks and estimated performance (2026-03-01)
Data last updated: 2026-03-15