Skip to content

Can RTX 4090 run Phi-4 14B?

Comfortable: GGUF Q5_K_M needs 11.8 GB at 4K, batch 1; headroom 12.2 GB.

Text input, FP16 KV cache, one card. Unified-memory capacity uses the GPU guide’s usable limit; negative headroom may require host offload. Speed source settings may differ from this 4K estimate.

Measured runs

FrameworkQuanttok/sVRAM used (GB)
llama.cppGGUF Q4_K_M889.1

Quant memory at 4K

QuantTotal GBVerdictWeight sizing
GGUF Q4_K_M10.2ComfortableEstimated weights
GGUF Q5_K_M11.8ComfortableEstimated weights
AWQ INT48.5ComfortableEstimated weights

Context capacity · GGUF Q5_K_M

ContextTotal GBVerdict
4K11.8Comfortable
16K14.3Comfortable

Generation speed

Measured: 88 tok/s, GGUF Q4_K_M, llama.cpp

GGUF Q5_K_M: 68–89 tok/s · Derived range

Other model / GPU pairs