← Back to Models
Microsofttransformer
Phi-4
14B parameters • 8.5GB VRAM (Q4 estimate) • 16,384 context
Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.
Specifications
Parameters
14B
VRAM (Q4 est.)
8.5 GB
VRAM (FP16)
28 GB
Context Window
16,384
Architecture
transformer
License
MIT
Finding cloud alternatives...
Run Phi-4 on RTX 3080
~8.5GB VRAM needed at Q4. RTX 3080 has 10GB — buy hardware or rent cloud.
We may earn a commission from cloud and hardware partners at no extra cost to you.
Find the cheapest GPU that can run Phi-4
Compatibility Lab — check every GPU × quantization combination