Can the Apple M2 Pro (32GB) run Gemma 2 9B?

Apple M2 Pro (32GB) × Gemma 2 9B8K context
YesRuns fully on the GPU
Memory at Q8_013.2 GB of 21.4 GB
Weights 9.8 GBKV cache 2.8 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Memory13.2 GBof 21.4 GB usable
Speed~12tokens 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 Gemma 2 9B fully in unified memory at Q8_0 (near-lossless), using about 13.2 GB of the 21.4 GB available, at roughly 12 tokens/second.

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 2 9B:

ollama run gemma2:9b

Ollama's default download is Q4_K_M (about 9 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No Apple M2 Pro (32GB)? Run Gemma 2 9B in the cloud.

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

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 quality21.9 GBToo big—
Q8_0Near-lossless13.2 GBFits~12 tok/s
Q6_KExcellent11 GBFits~16 tok/s
Q5_K_MVery good10 GBFits~18 tok/s
Q4_K_MGood, most popular9 GBFits~21 tok/s
Q3_K_MNoticeably degraded7.9 GBFits~27 tok/s
Q2_KHeavily degraded6.9 GBFits~35 tok/s

Frequently asked questions

Can Apple M2 Pro (32GB) run Gemma 2 9B?

Yes. The Apple M2 Pro (32GB) can run Gemma 2 9B fully in unified memory at Q8_0 (near-lossless), using about 13.2 GB of the 21.4 GB available, at roughly 12 tokens/second.

How much VRAM does Gemma 2 9B need?

About 9 GB at Q4_K_M with 8,192 tokens of context, and about 21.9 GB at full FP16 precision.

How fast is Gemma 2 9B on the Apple M2 Pro (32GB)?

Roughly 12 tokens per second at Q8_0, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.