Rent a GPU

Can the Apple M2 Pro (32GB) run Granite 3.3 8B?

Apple M2 Pro (32GB) × Granite 3.3 8B8K context
YesRuns fully on the GPU
Memory at FP1618.3 GB of 21.4 GB
Weights 16.3 GBKV cache 1.3 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~7tokens per second
Max context26Ktokens that fit at FP16
  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 Granite 3.3 8B fully in unified memory at FP16 (full quality), using about 18.3 GB of the 21.4 GB available, at roughly 7 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Granite 3.3 8B:

ollama run granite3.3:8b

Ollama's default download is Q4_K_M (about 6.9 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M2 Pro (32GB)

Run it in the cloud

No Apple M2 Pro (32GB)? Run Granite 3.3 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 quality18.3 GBFits~7 tok/s
Q8_0Near-lossless10.6 GBFits~14 tok/s
Q6_KExcellent8.6 GBFits~18 tok/s
Q5_K_MVery good7.8 GBFits~21 tok/s
Q4_K_MGood, most popular6.9 GBFits~24 tok/s
Q3_K_MNoticeably degraded5.9 GBFits~30 tok/s
Q2_KHeavily degraded5 GBFits~39 tok/s

Measured speed from real Apple M2 Pro (32GB) owners

Tokens per second that people measured on their own Apple M2 Pro (32GB), next to our estimate.

No one has measured Granite 3.3 8B on the Apple M2 Pro (32GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M2 Pro (32GB)? Add your real speed

One command times Granite 3.3 8B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- granite3.3:8b

Windows (PowerShell)

$env:GPUFIT_MODEL="granite3.3:8b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Granite 3.3 8B comfortably

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

Frequently asked questions

Can Apple M2 Pro (32GB) run Granite 3.3 8B?

Yes. The Apple M2 Pro (32GB) can run Granite 3.3 8B fully in unified memory at FP16 (full quality), using about 18.3 GB of the 21.4 GB available, at roughly 7 tokens/second.

How much VRAM does Granite 3.3 8B need?

About 6.9 GB at Q4_K_M with 8,192 tokens of context, and about 18.3 GB at full FP16 precision.

How fast is Granite 3.3 8B on the Apple M2 Pro (32GB)?

Roughly 7 tokens per second at FP16, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.