Gemma 4 31B on Apple M3 Pro (18GB Unified)

M3 Pro (18GB Unified) runs Gemma 4 31B at Q3_K_M — 7 tok/s due to limited memory bandwidth. Slow but functional — see all options below.

Model Size

30.7B

Device VRAM

18 GB

Bandwidth

150 GB/s

Quantization

Q3_K_M

Benchmarks

Performance by Quantization

OwnRig currently has one published compatibility entry for Gemma 4 31B on Apple M3 Pro (18GB Unified) at Q3_K_M. This is the best supported pairing we can stand behind today.

Quantization	Speed	TTFT	Fits in VRAM	Rating	Confidence
Q3_K_M	7 tok/s	1500ms	✓ Yes	Marginal	estimated

Notes

Q3_K_M

30.7B model. Q3_K_M 14.59GB on 18GB apple_silicon.

About Gemma 4 31B

Gemma 4 31B (30.7B) is a chat, coding, reasoning, multi-purpose model. Google's flagship open-weight model. Dense 30.7B parameters with 256K context. Benchmarks: 89.2% AIME 2026, 85.2% MMLU Pro, 84.3% GPQA Diamond, 80.0% LiveCodeBench v6, 86.4% agentic tool use. Supports text, image, and video input. Fits on a single RTX 4090 at Q4 or dual 16 GB GPUs. Direct successor to Gemma 3 27B with substantially better reasoning. Apache 2.0 licensed.

View all Gemma 4 31B hardware options →

About Apple M3 Pro (18GB Unified)

Apple M3 Pro (18GB Unified) has 18 GB at 150 GB/s. Available in MacBook Pro 14", MacBook Pro 16".

See all models Apple M3 Pro (18GB Unified) can run →

Estimate method: Estimated from model architecture, quantization size, and device bandwidth. Reference hardware source: huggingface.co (2026-04-04)

Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.