GPUFits
Can RTX 3060 12GB run Phi-4 14B?
🔀 Needs multi-GPU
Phi-4 14B @ Q4_K_M · 8K context
Needed
12.2 GB
Usable
12.0 GB
VRAM breakdown
| Weights (Q4_K_M) | 9.0 GB |
| KV cache (8K context) | 1.7 GB |
| Runtime overhead | 1.5 GB |
| Total | 12.2 GB |
Computed at 8K context with fp16 KV cache. Longer contexts need more VRAM — use the VRAM calculator for other settings.
Recommended quantization
Q3_K_M
Estimated generation speed
~37 tok/s @ Q3_K_M
Theoretical estimates based on published architecture data and measured GGUF sizes; real-world speed varies ±30%.
Smaller models this GPU runs well
FAQ
- How much VRAM does Phi-4 14B need?
- At Q4_K_M with 8K context: 9.0GB weights + 1.7GB KV cache + 1.5GB runtime overhead = 12.2GB total. RTX 3060 12GB offers 12.0GB usable VRAM, so the verdict is: Needs multi-GPU.
- What is the best quantization for Phi-4 14B on RTX 3060 12GB?
- Q3_K_M — the highest tier that still fits within 12.0GB usable VRAM at 8K context. Lower tiers (Q3/Q2) fit too but cost noticeable quality.
- How fast does Phi-4 14B run on RTX 3060 12GB?
- About 37 tokens/s at Q3_K_M (theoretical estimate, ±30% in real-world use).
Check another combination in the GPU Checker →
Data verified 2026-08-04