Gemma 4 26B-A4B on Apple M3 Pro (18GB Unified)

Yes — M3 Pro (18GB Unified) handles Gemma 4 26B-A4B well at Q3_K_M — 51 tok/s. Solid daily-driver performance on 18 GB VRAM.

Model Size

25.2B

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 26B-A4B 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	51 tok/s	100ms	✓ Yes	Good	estimated

Notes

Q3_K_M

25.2B model. Q3_K_M 12.36GB on 18GB apple_silicon.

About Gemma 4 26B-A4B

Gemma 4 26B-A4B (25.2B) is a chat, coding, reasoning, multi-purpose model. Mixture-of-Experts architecture: 25.2B total parameters but only 3.8B active per token (8 selected + 1 shared expert per layer, out of 128 total). Hybrid dense+sparse FFN design. Inference throughput closer to a 4B dense model; quality closer to a 27B dense model. 256K context window. Benchmarks: 88.3% AIME 2026, 82.6% MMLU Pro, 77.1% LiveCodeBench. All 25.2B weights must be loaded into VRAM despite sparse activation; fits on 24 GB GPUs at Q4_K_M. Apache 2.0 licensed.

View all Gemma 4 26B-A4B 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 MoE active params (3.8B), quantization, and device bandwidth with 0.65 efficiency factor. 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.