Rent a GPU

Can the Apple M1 Max (64GB) run Gemma 2 27B?

Apple M1 Max (64GB) × Gemma 2 27B8K context
YesRuns fully on the GPU
Memory at Q8_031.8 GB of 48 GB
Weights 28.9 GBKV cache 2.3 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~8tokens per second
Max context8Kthe model's full window
  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 M1 Max (64GB) can run Gemma 2 27B fully in unified memory at Q8_0 (near-lossless), using about 31.8 GB of the 48 GB available, at roughly 8 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 2 27B:

ollama run gemma2:27b

Ollama's default download is Q4_K_M (about 19.4 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M1 Max (64GB)

Run it in the cloud

No Apple M1 Max (64GB)? Run Gemma 2 27B 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 48 GB the Apple M1 Max (64GB) can use. macOS lets the GPU use about 48 GB of the 64 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality57.3 GBToo big—
Q8_0Near-lossless31.8 GBFits~8 tok/s
Q6_KExcellent25.2 GBFits~11 tok/s
Q5_K_MVery good22.3 GBFits~12 tok/s
Q4_K_MGood, most popular19.4 GBFits~15 tok/s
Q3_K_MNoticeably degraded16.2 GBFits~18 tok/s
Q2_KHeavily degraded13.1 GBFits~24 tok/s

Measured speed from real Apple M1 Max (64GB) owners

Tokens per second that people measured on their own Apple M1 Max (64GB), next to our estimate.

No one has measured Gemma 2 27B on the Apple M1 Max (64GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M1 Max (64GB)? Add your real speed

One command times Gemma 2 27B 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 -- gemma2:27b

Windows (PowerShell)

$env:GPUFIT_MODEL="gemma2:27b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Gemma 2 27B comfortably

Models that run well on the Apple M1 Max (64GB)

Frequently asked questions

Can Apple M1 Max (64GB) run Gemma 2 27B?

Yes. The Apple M1 Max (64GB) can run Gemma 2 27B fully in unified memory at Q8_0 (near-lossless), using about 31.8 GB of the 48 GB available, at roughly 8 tokens/second.

How much VRAM does Gemma 2 27B need?

About 19.4 GB at Q4_K_M with 8,192 tokens of context, and about 57.3 GB at full FP16 precision.

How fast is Gemma 2 27B on the Apple M1 Max (64GB)?

Roughly 8 tokens per second at Q8_0, estimated from the Apple M1 Max (64GB)'s 400 GB/s memory bandwidth.