Phi-4 Mini on NVIDIA GeForce RTX 5090
NVIDIA GeForce RTX 5090 runs Phi-4 Mini excellently at 185 tok/s at Q8_0. This is a strong pairing.
Model Size
3.82B
Device VRAM
32 GB
Bandwidth
1792 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Phi-4 Mini performance at a different quality level on NVIDIA GeForce RTX 5090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q8_0 | 185 tok/s | 22ms | ✓ Yes | Excellent | estimated |
Notes
Q8_0
1792 GB/s. Maximum Phi-4 mini speed.
About Phi-4 Mini
Phi-4 Mini (3.82B) is a chat, coding, ai coding, reasoning model. Microsoft's tiny powerhouse. Punches well above its weight at 3.8B parameters — competitive with many 7B models on reasoning and coding benchmarks. Extremely fast inference. Ideal as a draft model or for resource-constrained setups.
View all Phi-4 Mini hardware options →About NVIDIA GeForce RTX 5090
NVIDIA GeForce RTX 5090 has 32 GB at 1792 GB/s. Street price: $2,199.
See all models NVIDIA GeForce RTX 5090 can run →Builds with NVIDIA GeForce RTX 5090
Source: Performance estimates based on model size and device bandwidth (2026-03-15)
Data last updated: 2026-03-15