Phi-4 14B on NVIDIA GeForce RTX 4070 Ti Super
NVIDIA GeForce RTX 4070 Ti Super handles Phi-4 14B well at 42 tok/s at Q5_K_M. A solid choice for this model.
Model Size
14.7B
Device VRAM
16 GB
Bandwidth
672 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Phi-4 14B performance at a different quality level on NVIDIA GeForce RTX 4070 Ti Super.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 42 tok/s | 170ms | ✓ Yes | Good | estimated |
Notes
Q5_K_M
Q5 fits with headroom. Strong reasoning performance.
About Phi-4 14B
Phi-4 14B (14.7B) is a reasoning, coding, chat model. Microsoft's efficient reasoning and coding model with strong performance per parameter.
View all Phi-4 14B hardware options →About NVIDIA GeForce RTX 4070 Ti Super
NVIDIA GeForce RTX 4070 Ti Super has 16 GB at 672 GB/s. Street price: $779.
See all models NVIDIA GeForce RTX 4070 Ti Super can run →Source: Community benchmarks and estimated performance (2026-03-01)
Data last updated: 2026-03-15