Gemma 4 26B-A4B on Apple M4 Pro (24GB Unified)

Yes — M4 Pro (24GB Unified) runs Gemma 4 26B-A4B excellently at Q4_K_M — 71 tok/s. 24 GB VRAM with plenty of headroom.

Model Size

25.2B

Device VRAM

24 GB

Bandwidth

273 GB/s

Quantization

Q4_K_M

Benchmarks

Performance by Quantization

OwnRig currently has one published compatibility entry for Gemma 4 26B-A4B on Apple M4 Pro (24GB Unified) at Q4_K_M. This is the best supported pairing we can stand behind today.

Quantization	Speed	TTFT	Fits in VRAM	Rating	Confidence
Q4_K_M	71 tok/s	50ms	✓ Yes	Excellent	estimated

Notes

Q4_K_M

25.2B model. Q5_K_M 19.32GB on 24GB 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 M4 Pro (24GB Unified)

Apple M4 Pro (24GB Unified) has 24 GB at 273 GB/s. Available in MacBook Pro 14", MacBook Pro 16", Mac Mini.

See all models Apple M4 Pro (24GB Unified) can run →

Estimate method: Estimated from MoE active params (3.8B), Q4_K_M quantization, and M4 Pro bandwidth with 0.65 efficiency factor. Q5_K_M does not fit after macOS memory overhead.. 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.