OwnRig

Gemma 2 9B Instruct on Apple M3 Pro (18GB Unified)

Apple M3 Pro (18GB Unified) can run Gemma 2 9B Instruct at 13 tok/s at Q4_K_M, though performance is acceptable. Consider a higher-end GPU for better results.

Model Size

9.24B

Device VRAM

18 GB

Bandwidth

150 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Gemma 2 9B Instruct performance at a different quality level on Apple M3 Pro (18GB Unified).

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q4_K_M13 tok/s450ms✓ YesAcceptableestimated

Notes

Q4_K_M

Slower than M4 Pro. Usable for chat and light coding.

About Gemma 2 9B Instruct

Gemma 2 9B Instruct (9.24B) is a chat, coding, reasoning, multi-purpose model. Google's 9B model with strong knowledge distillation. Competitive with Llama 3.1 8B on most benchmarks. Shorter max context (8K) is the main limitation vs Llama.

View all Gemma 2 9B 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