Phi
How much VRAM does Phi-3 Medium 14B need?
Phi-3 Medium 14B has 14B parameters, so its weights alone take about 28 GB of VRAM at FP16 — or roughly 7 GB quantized to INT4. Real serving adds KV cache on top, which scales with your context length and concurrent requests. Size the exact figure for your workload below.
Total params
14B
Active params
14B
Layers
40
Hidden size
5120
Attention heads
40
KV heads (GQA)
10
Vocab size
32,064
Native context window
131,072
Native precision
BF16
Size Phi-3 Medium 14B for your workload
Opens the free calculator with Phi-3 Medium 14B loaded at BF16 weights and FP16 KV cache. Set your context length and traffic to get exact GPU memory and a ranked list of cloud instances that fit — no signup.
Size this model →