Run Gemma 4 26B-A4B on M4 Pro

Yes — Gemma 4 26B-A4B (26B) runs at 28 tok/s on M4 Pro with 24 GB RAM using Q4_K_M quantization via Ollama. First token latency is 1.0s. Google's 26B MoE model activating only 3.8B params — near-frontier quality at 24 GB.

Speed
28
tok/s
First Token
1.0
seconds
RAM Needed
24
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Gemma 4 26B-A4B on M4 Pro 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 second28 tok/s
Time to first token1.0s
QuantizationQ4_K_M
Minimum RAM24 GB
Recommended engineOllama
Parameters26B
Benchmark date2026-04

Q4_K_M 26B Ollama M4 Pro

Setup Guide: Run Gemma 4 26B-A4B on M4 Pro

The recommended engine for Gemma 4 26B-A4B on M4 Pro is Ollama. Install Ollama, then pull the model:

ollama run gemma4:26b-a4b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~24 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 50 tok/s 0.5s 128 GB MLX
M4 Max 40 tok/s 0.7s 48 GB MLX
M5 Pro 35 tok/s 0.8s 24 GB Ollama

System Requirements

To run Gemma 4 26B-A4B on M4 Pro you need:

Compare More Models

See how Gemma 4 26B-A4B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard