Phi-4 14B on NVIDIA GeForce RTX 4080 Super
NVIDIA GeForce RTX 4080 Super runs Phi-4 14B excellently at 48 tok/s at Q5_K_M. This is a strong pairing.
Model Size
14.7B
Device VRAM
16 GB
Bandwidth
736 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Phi-4 14B performance at a different quality level on NVIDIA GeForce RTX 4080 Super.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 48 tok/s | 150ms | ✓ Yes | Excellent | estimated |
Notes
Q5_K_M
14B Q5 fits on 16GB. Good reasoning speed.
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 4080 Super
NVIDIA GeForce RTX 4080 Super has 16 GB at 736 GB/s. Street price: $979.
See all models NVIDIA GeForce RTX 4080 Super can run →Source: Community benchmarks and estimated performance (2026-03-01)
Data last updated: 2026-03-15