Phi-4 Mini cost & VRAM calculator
What does Phi-4 Mini cost to run for your workload, and can you run it on your own hardware? Set your workload below - we compute per-provider API cost live and tell you honestly whether local hardware can run it.
Your workload
API cost for your workload
No per-token API provider pricing tracked for Phi-4 Mini yet. For flagship list prices, see the generic calculator.
Can you run it locally?
YES - IT RUNS ON HARDWARE YOU CAN BUY
Phi-4 Mini fits on individual rigs. Here's the hardware that runs it comfortably; the full per-quant VRAM matrix and tok/s estimates live on the model page.
4x H100 80GB (320GB)
320GB
Q4_K_M
2219.9t/s
NVIDIA DGX Station 748GB
748GB
Q4_K_M
1325.3t/s
8x RTX 3090 rack (192GB)
192GB
Q4_K_M
1240.8t/s
4x RTX 5090 (128GB)
128GB
Q4_K_M
1187.5t/s
AMD Instinct MI300X (192GB)
192GB
Q4_K_M
882.1t/s
4x RTX 4090 (96GB)
96GB
Q4_K_M
668.0t/s
2x RTX 5090 (64GB)
64GB
Q4_K_M
593.7t/s
2x RTX 3090 (48GB)
48GB
Q4_K_M
310.2t/s
Single RTX 5090 (32GB)
32GB
Q4_K_M
296.9t/s
RTX PRO 6000 Blackwell (96GB)
96GB
Q4_K_M
296.9t/s
Mac Studio M4 Ultra 192GB
192GB
Q4_K_M
197.4t/s
Mac Studio M4 Ultra 512GB
512GB
Q4_K_M
197.4t/s
Single RTX 4090 (24GB)
24GB
Q4_K_M
167.0t/s
MacBook Pro M5 Max 128GB
128GB
Q4_K_M
111.0t/s
Single GTX 1080 Ti (11GB)
11GB
Q4_K_M
80.2t/s
Dual EPYC 9004 + 768GB DDR5-4800
768GB
Q4_K_M
76.3t/s
DGX Spark 128GB unified
128GB
Q4_K_M
45.2t/s
Ryzen AI Max+ 395 128GB
128GB
Q4_K_M
42.4t/s
Jetson AGX Orin 64GB
64GB
Q4_K_M
33.9t/s
Epyc + 512GB DDR4-3200 + 2x RTX 3090
560GB
Q4_K_M
33.9t/s
Epyc + 512GB DDR4-2400 + 2x RTX 3090
560GB
Q4_K_M
25.5t/s
NVIDIA Jetson Orin NX 16GB
16GB
Q4_K_M
17.0t/s
Q4_K_M
2.5GB weights
2.5GB min
3.7GB rec
Q8_0
4.1GB weights
4.1GB min
5.3GB rec
Want the own-vs-rent payback (capex vs your monthly API bill)? The budget tool computes that against representative rigs.