Rent a GPU

Can the Apple M2 Pro (32GB) run Phi-3.5 Mini 3.8B?

Apple M2 Pro (32GB) × Phi-3.5 Mini 3.8B8K context
YesRuns fully on the GPU
Memory at FP1611.5 GB of 21.4 GB
Weights 7.6 GBKV cache 3.2 GBRuntime 0.6 GB
QuantFP16Full quality
Memory11.5 GBof 21.4 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 Pro (32GB) can run Phi-3.5 Mini 3.8B fully in unified memory at FP16 (full quality), using about 11.5 GB of the 21.4 GB available, at roughly 16 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Phi-3.5 Mini 3.8B:

ollama run phi3.5:3.8b

Ollama's default download is Q4_K_M (about 6.1 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 Pro (32GB)? Run Phi-3.5 Mini 3.8B 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 21.4 GB the Apple M2 Pro (32GB) can use. macOS lets the GPU use about 21.4 GB of the 32 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality11.5 GBFits~16 tok/s
Q8_0Near-lossless7.9 GBFits~30 tok/s
Q6_KExcellent7 GBFits~38 tok/s
Q5_K_MVery good6.5 GBFits~44 tok/s
Q4_K_MGood, most popular6.1 GBFits~52 tok/s
Q3_K_MNoticeably degraded5.7 GBFits~64 tok/s
Q2_KHeavily degraded5.3 GBFits~84 tok/s

GPUs that run Phi-3.5 Mini 3.8B comfortably

Models that run well on the Apple M2 Pro (32GB)

Frequently asked questions

Can Apple M2 Pro (32GB) run Phi-3.5 Mini 3.8B?

Yes. The Apple M2 Pro (32GB) can run Phi-3.5 Mini 3.8B fully in unified memory at FP16 (full quality), using about 11.5 GB of the 21.4 GB available, at roughly 16 tokens/second.

How much VRAM does Phi-3.5 Mini 3.8B need?

About 6.1 GB at Q4_K_M with 8,192 tokens of context, and about 11.5 GB at full FP16 precision.

How fast is Phi-3.5 Mini 3.8B on the Apple M2 Pro (32GB)?

Roughly 16 tokens per second at FP16, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.