Gemma 3 4B on NVIDIA GeForce RTX 4070 Super
NVIDIA GeForce RTX 4070 Super runs Gemma 3 4B excellently at 85 tok/s at Q8_0. This is a strong pairing.
Model Size
4.3B
Device VRAM
12 GB
Bandwidth
504 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Gemma 3 4B performance at a different quality level on NVIDIA GeForce RTX 4070 Super.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q8_0 | 85 tok/s | 65ms | ✓ Yes | Excellent | estimated |
Notes
Q8_0
4B at Q8. Minimal VRAM, fast inference.
About Gemma 3 4B
Gemma 3 4B (4.3B) is a chat, coding model. Compact Gemma 3 model for chat and light coding on low-VRAM hardware.
View all Gemma 3 4B hardware options →About NVIDIA GeForce RTX 4070 Super
NVIDIA GeForce RTX 4070 Super has 12 GB at 504 GB/s. Street price: $599.
See all models NVIDIA GeForce RTX 4070 Super can run →Builds with NVIDIA GeForce RTX 4070 Super
Source: Community benchmarks and estimated performance (2026-03-01)
Data last updated: 2026-03-15