Phi-4
29 consumer GPUs can run Phi-4 at Q4 natively. Precise VRAM thresholds and benchmarks below.
llama.cpp 0.2.x · CUDA 12 · ROCm 6 · Updated monthly · methodology →
Execution Context
This model requires a Mid-range GPU (16 GB VRAM)
Cómo ejecutar este modelo
Check if your GPU can run Phi-4 →
VRAM Calculator — instant compatibility check
RTX 5090
32 GB · Runs Q4 natively · Check availability
*Prices and availability may change. Some links are affiliate links.
System Requirements
VRAM by Quantization
| Quantization | VRAM needed | Disk space | Quality |
|---|---|---|---|
| FP16 (max quality) | 33.6 GB | 28 GB | Maximum |
| Q8 (high quality) | 16.8 GB | 14 GB | Near-lossless |
| Q4 (recommended) Best balance | 8.4 GB | 7 GB | Recommended |
| Q2 (minimum) | 4.2 GB | 3.5 GB | Quality loss |
Model Details
| Developer | Microsoft |
| Parameters | 14B |
| Context window | 16,384 tokens |
| License | MIT |
| Use cases | chat, coding, reasoning, analysis |
| Released | 2024-12 |
Install with Ollama
ollama run phi4:14b Hugging Face
microsoft/phi-4 Can your GPU run Phi-4?
Phi-4 requires 8.4 GB VRAM at Q4. 29 consumer GPUs meet this threshold. Below 8 GB or 6.4 GB you'll hit significant offload latency.
Hardware Performance Matrix
29 Q4 native · 11 offload · 0 unsupported
Recommended GPUs for Phi-4
Best picks by compatibility, VRAM headroom, and value — prices and availability may change.
RTX 5090
32 GB VRAM
Check availability →
RTX 4090
24 GB VRAM
Check availability →
M4 Ultra
128 GB VRAM
Check availability →
Some links are Amazon affiliate links. We may earn a commission at no extra cost to you. Amazon cookies may last up to 24 hours after your click.
Phi-4 — Compatibility guide
Phi-4 needs intermediate hardware or Q4 quantization to run on consumer GPUs. With 10 GB VRAM you get the best quality. Use the VRAM calculator to see which quantization your GPU supports.
Compare GPUs for Phi-4
Which GPU is worth it? Real specs and benchmarks side by side.
Compatible Hardware
GPUs that run Phi-4 at Q4 — sorted by AI performance score.
Some links are Amazon affiliate links. We may earn a commission at no extra cost to you. Amazon cookies may last up to 24 hours after your click.
More Practical Alternatives
Similar models in the chat category with comparable VRAM footprints.
Compare This Model
See how Phi-4 stacks up in head-to-head comparisons.
Not sure which GPU you need for Phi-4?
The VRAM Calculator tells you exactly which quantization your hardware can handle.