Gemma 4 26B-A4B on Apple M1 Pro (16GB Unified)

M1 Pro (16GB Unified) cannot run Gemma 4 26B-A4B. 16 GB VRAM is insufficient at any quantization level.

Model Size

25.2B

Device VRAM

16 GB

Bandwidth

200 GB/s

Quantization

Q3_K_M

Benchmarks

Performance by Quantization

OwnRig currently has one published compatibility entry for Gemma 4 26B-A4B on Apple M1 Pro (16GB Unified) at Q3_K_M. This pairing has limitations — check the rating and notes below.

Quantization	Speed	TTFT	Fits in VRAM	Rating	Confidence
Q3_K_M	–	–	✗ Offload	Not viable	estimated

Notes

Q3_K_M

Model exceeds m1-pro-16gb effective VRAM capacity.

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 M1 Pro (16GB Unified)

Apple M1 Pro (16GB Unified) has 16 GB at 200 GB/s. Available in MacBook Pro 14" (2021), MacBook Pro 16" (2021).

See all models Apple M1 Pro (16GB Unified) can run →

Estimate method: Estimated: model exceeds m1-pro-16gb VRAM capacity. Reference hardware source: github.com (2026-04-18)

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.