Rent a GPU

Can the Apple M2 Ultra (192GB) run Phi-4 14B?

Apple M2 Ultra (192GB) × Phi-4 14B8K context
YesRuns fully on the GPU
Memory at FP1631.7 GB of 144 GB
Weights 29.4 GBKV cache 1.7 GBRuntime 0.6 GB
QuantFP16Full quality
Memory31.7 GBof 144 GB usable
Speed~16tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The Apple M2 Ultra (192GB) can run Phi-4 14B fully in unified memory at FP16 (full quality), using about 31.7 GB of the 144 GB available, at roughly 16 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Phi-4 14B:

ollama run phi4:14b

Ollama's default download is Q4_K_M (about 11.2 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No Apple M2 Ultra (192GB)? Run Phi-4 14B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 144 GB the Apple M2 Ultra (192GB) can use. macOS lets the GPU use about 144 GB of the 192 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality31.7 GBFits~16 tok/s
Q8_0Near-lossless17.9 GBFits~31 tok/s
Q6_KExcellent14.3 GBFits~40 tok/s
Q5_K_MVery good12.7 GBFits~46 tok/s
Q4_K_MGood, most popular11.2 GBFits~54 tok/s
Q3_K_MNoticeably degraded9.5 GBFits~67 tok/s
Q2_KHeavily degraded7.8 GBFits~87 tok/s

GPUs that run Phi-4 14B comfortably

Models that run well on the Apple M2 Ultra (192GB)

Frequently asked questions

Can Apple M2 Ultra (192GB) run Phi-4 14B?

Yes. The Apple M2 Ultra (192GB) can run Phi-4 14B fully in unified memory at FP16 (full quality), using about 31.7 GB of the 144 GB available, at roughly 16 tokens/second.

How much VRAM does Phi-4 14B need?

About 11.2 GB at Q4_K_M with 8,192 tokens of context, and about 31.7 GB at full FP16 precision.

How fast is Phi-4 14B on the Apple M2 Ultra (192GB)?

Roughly 16 tokens per second at FP16, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.