Run Gemma 4.5 12B on M3

Yes — Gemma 4.5 12B (12B) runs at 42 tok/s on M3 with 16 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.8s. A capable open-source LLM with 12B parameters.

Speed
42
tok/s
First Token
0.8
seconds
RAM Needed
16
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Gemma 4.5 12B on M3 using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.

MetricValue
Tokens per second42 tok/s
Time to first token0.8s
QuantizationQ4_K_M
Minimum RAM16 GB
Recommended engineOllama
Parameters12B
Benchmark date2026-06

Q4_K_M 12B Ollama M3

Setup Guide: Run Gemma 4.5 12B on M3

The recommended engine for Gemma 4.5 12B on M3 is Ollama. Install Ollama, then pull the model:

ollama run gemma-45-12b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~16 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 75 tok/s 0.4s 128 GB MLX
M4 Pro 58 tok/s 0.5s 24 GB MLX
M5 Pro 52 tok/s 0.6s 24 GB Ollama
M2 35 tok/s 1.0s 16 GB Ollama

System Requirements

To run Gemma 4.5 12B on M3 you need:

Compare More Models

See how Gemma 4.5 12B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard