OwnRig

Gemma 2 27B Instruct on Apple M3 Pro (18GB Unified)

Apple M3 Pro (18GB Unified) cannot run Gemma 2 27B Instruct at any quantization level. The 18 GB of VRAM is insufficient.

Model Size

27.23B

Device VRAM

18 GB

Bandwidth

150 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Gemma 2 27B Instruct performance at a different quality level on Apple M3 Pro (18GB Unified).

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q4_K_M✗ OffloadNot Viableestimated

Notes

Q4_K_M

Q4 16.3GB exceeds 14GB effective. Doesn't fit.

About Gemma 2 27B Instruct

Gemma 2 27B Instruct (27.23B) is a chat, coding, reasoning, multi-purpose model. Google's 27B model with excellent knowledge distillation. Strong reasoning and coding capabilities at a size that fits on a single 24GB GPU at Q4. Limited to 8K context.

View all Gemma 2 27B Instruct 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 →

Source: MLX performance estimates (2026-03-15)

Data last updated: 2026-03-01