Yes — Gemma 4.5 27B (27B) runs at 42 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.6s. A capable open-source LLM with 27B parameters.
LLMCheck measured Gemma 4.5 27B on M5 Max using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.
| Metric | Value |
|---|---|
| Tokens per second | 42 tok/s |
| Time to first token | 0.6s |
| Quantization | Q4_K_M |
| Minimum RAM | 128 GB |
| Recommended engine | MLX |
| Parameters | 27B |
| Benchmark date | 2026-07 |
Q4_K_M 27B MLX M5 Max
The recommended engine for Gemma 4.5 27B on M5 Max is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M4 Max | 36 tok/s | 0.7s | 48 GB | MLX |
| M3 Max | 32 tok/s | 0.9s | 64 GB | Ollama |
| M5 Pro | 30 tok/s | 0.9s | 32 GB | Ollama |
| M4 Pro | 26 tok/s | 1.0s | 32 GB | Ollama |
To run Gemma 4.5 27B on M5 Max you need:
Gemma 4.5 27B needs about 128 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
Not sure which Mac fits your budget? See the best Mac for running this →
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.
See how Gemma 4.5 27B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard