How much VRAM to run Phi-4?

About 13 GB atQ4_K_M with an 8K context — fits a RTX 5060 Ti 16GB. Full breakdown below, or check your exact hardware.

Phi-4 VRAM by quantisation

QuantisationWeightsTotal (8K ctx)Fits on
Q4_K_M9.0 GB12.7 GBRTX 5060 Ti 16GB, RX 7900 XTX
Q5_K_M10.5 GB14.4 GBRTX 5060 Ti 16GB, RX 7900 XTX
Q6_K12.1 GB16.1 GBRX 7900 XTX, RTX 4090
Q8_015.7 GB20.1 GBRX 7900 XTX, RTX 4090
FP16 / BF1629.4 GB35.2 GBApple Silicon 48GB unified, RTX 6000 Ada

Check your hardware

About Phi-4

Phi-4 is Microsoft's 14.7B-parameter model released in December 2024, with a 16K-token context window. It uses a classic dense-attention design whose KV cache grows linearly with context: its KV cache is about 1.7 GB at an 8K context, 3.4 GB at 16K, and 3.4 GB at the full 16K window (FP16 cache).

For most people Q4_K_M is the sweet spot — the most popular quality/size trade-off — while Q8 is near-lossless if you have the memory. Totals above include the KV cache and a realistic framework overhead, so they are what you should expect to see in practice rather than just the download size. Weight sizes are calibrated against real GGUF files — see themethodology.

Frequently asked questions

How much VRAM does Phi-4 need?

At Q4_K_M with an 8K context, Phi-4 needs about 13 GB (weights 9 GB + KV cache + overhead). The smallest common hardware that fits is a RTX 5060 Ti 16GB.

Can an RTX 4090 (24GB) run Phi-4?

Yes. An RTX 4090's 24 GB runs Phi-4 at Q8_0 (about 20 GB at 8K context).

Can a Mac run Phi-4?

Yes — Apple Silicon with 24 GB of unified memory or more (macOS lets the GPU use ~75% of it, ~18 GB) runs Phi-4 at Q4_K_M.

Related

VRAM calculator for any model ·Token counter

Last updated 2026-08-03. Architecture figures from the model's published config.json; see themethodology.