Rent a GPU

Can the Apple M2 Ultra (192GB) run Gemma 2 9B?

Apple M2 Ultra (192GB) × Gemma 2 9B8K context
YesRuns fully on the GPU
Memory at FP1621.9 GB of 144 GB
Weights 18.5 GBKV cache 2.8 GBRuntime 0.6 GB
QuantFP16Full quality
Memory21.9 GBof 144 GB usable
Speed~26tokens 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 Gemma 2 9B fully in unified memory at FP16 (full quality), using about 21.9 GB of the 144 GB available, at roughly 26 tokens/second.

Try other context lengths

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 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 Gemma 2 9B 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 quality21.9 GBFits~26 tok/s
Q8_0Near-lossless13.2 GBFits~49 tok/s
Q6_KExcellent11 GBFits~63 tok/s
Q5_K_MVery good10 GBFits~73 tok/s
Q4_K_MGood, most popular9 GBFits~86 tok/s
Q3_K_MNoticeably degraded7.9 GBFits~106 tok/s
Q2_KHeavily degraded6.9 GBFits~139 tok/s

GPUs that run Gemma 2 9B comfortably

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

Frequently asked questions

Can Apple M2 Ultra (192GB) run Gemma 2 9B?

Yes. The Apple M2 Ultra (192GB) can run Gemma 2 9B fully in unified memory at FP16 (full quality), using about 21.9 GB of the 144 GB available, at roughly 26 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 Ultra (192GB)?

Roughly 26 tokens per second at FP16, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.