Can the Apple M2 Pro (32GB) run Gemma 2 27B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
Yes. The Apple M2 Pro (32GB) can run Gemma 2 27B fully in unified memory at Q4_K_M (good, most popular), using about 20.2 GB of the 21.4 GB available, at roughly 7 tokens/second.
Run it with Ollama
With Ollama installed, one command downloads and starts Gemma 2 27B:
ollama run gemma2:27bOllama's default download is Q4_K_M (about 20.2 GB here). That is also the best quant that fits.
Run it in the cloud
No Apple M2 Pro (32GB)? Run Gemma 2 27B 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.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 58.1 GB | Too big | — | |
| Q8_0 | Near-lossless | 32.6 GB | Too big | — | |
| Q6_K | Excellent | 26 GB | Too big | — | |
| Q5_K_M | Very good | 23 GB | Too big | — | |
| Q4_K_M | Good, most popular | 20.2 GB | Fits | ~7 tok/s | |
| Q3_K_M | Noticeably degraded | 17 GB | Fits | ~9 tok/s | |
| Q2_K | Heavily degraded | 13.9 GB | Fits | ~12 tok/s |
GPUs that run Gemma 2 27B comfortably
Frequently asked questions
Can Apple M2 Pro (32GB) run Gemma 2 27B?
Yes. The Apple M2 Pro (32GB) can run Gemma 2 27B fully in unified memory at Q4_K_M (good, most popular), using about 20.2 GB of the 21.4 GB available, at roughly 7 tokens/second.
How much VRAM does Gemma 2 27B need?
About 20.2 GB at Q4_K_M with 8,192 tokens of context, and about 58.1 GB at full FP16 precision.
How fast is Gemma 2 27B on the Apple M2 Pro (32GB)?
Roughly 7 tokens per second at Q4_K_M, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.