Dedicated GPU memory guides
These Windows/NVIDIA guide pages use dedicated GPU memory as the primary fit budget and keep partial offload separate from a full GPU fit.
Microsoft · Phi
Phi-4 local AI fit guide
Review available GGUF variants, quantization choices, and conservative memory-planning levels for running Phi-4locally.
- Parameters
- 14B
- Size class
- medium
- Use cases
- chat, reasoning, coding
GGUF variants
| Variant | Quantization | Estimated file | Minimum load | Planning memory |
|---|---|---|---|---|
| Phi-4 · Q4_K_M | Q4_K_M | 8.1 GB | 9.3 GB | 10.9 GB |
GPU compatibility
GPUs with a verified memory-fit path for Phi-4
These pages compare this model's recorded GGUF variants against the dedicated VRAM of selected NVIDIA GPUs. They are deterministic memory-fit checks, not performance benchmarks.
Apple Silicon unified-memory guides
Apple Silicon pages use conservative unified-memory budgets and Metal-capable local inference terminology instead of treating the Mac as a CUDA workstation.
Fit caveats
These are deterministic memory-planning checks, not benchmark claims. Context length, runtime settings, offload behavior, and concurrent apps can change practical fit.