text model · gemma · macOS
Can I run Gemma 2 27B on Apple M3 Ultra (256GB)?
Yes. Gemma 2 27B runs on Apple M3 Ultra (256GB) at Q4_K_M (~18.7 GB of ~192 GB usable).
Runs at Q4_K_M using ~18.7 GB of ~192 GB usable. You have room for FP16 for higher quality.
- Q4_K_M needed
- ~18.7 GB
- Usable on device
- ~192 GB
- Device memory
- 256 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run gemma2:27b llama-cli -hf bartowski/gemma-2-27b-it-GGUF:Q4_K_M lms get bartowski/gemma-2-27b-it-GGUF vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
- Parameters
- 27B
- Q4_K_M size
- 16.65 GB
- Q8_0 size
- 28.94 GB
- Context
- 8k
- Ollama tag
- gemma2:27b
- Memory
- 256 GB unified
- Usable for weights
- ~192 GB
- Best runtime
- MLX direct / Ollama (MLX backend)
You could also run
Run Gemma 2 27B on other hardware
FAQ
Can Apple M3 Ultra (256GB) run Gemma 2 27B?
Yes. Gemma 2 27B runs on Apple M3 Ultra (256GB) at Q4_K_M (~18.7 GB of ~192 GB usable).
How much memory does Gemma 2 27B need?
Apple M3 Ultra (256GB) has room to spare. At Q4_K_M the weights are ~16.65 GB; with KV cache and runtime overhead, budget ~18.7 GB at a 4k context.
What is the best tool to run Gemma 2 27B on macOS?
LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
Sources
Memory figures are estimates. See methodology.