Microsoft

Phi-4

Microsoft's 14B parameter model. Punches well above its weight on reasoning.

14B parametersphi3mit16K context8.93GB - 15.01GB VRAM

Check Your Hardware

See which quantizations of Phi-4 your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
Q4_K_M4.58.431 GB8.93 GB9.43 GB
85%
Q5_K_M5.59.876 GB10.38 GB10.88 GB
90%
Q8_0814.51 GB15.01 GB15.51 GB
98%

See It In Action

Real model outputs generated via RunThisModel.com — watch responses stream in real time.

Llama 3.3 70B responding...

Outputs generated by real AI models via RunThisModel.com. Generation speed shown is from cloud inference. Local speeds vary by hardware — check your device.

Frequently Asked Questions

How much VRAM do I need to run Phi-4?

Phi-4 requires 8.93GB VRAM minimum with Q4_K_M quantization. For full precision, you need 15.01GB VRAM.

What is the best quantization for Phi-4?

Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.