OwnRig

Qwen 2.5 Coder 7B Instruct on Apple M3 Pro (18GB Unified)

Apple M3 Pro (18GB Unified) can run Qwen 2.5 Coder 7B Instruct at 15 tok/s at Q4_K_M, though performance is acceptable. Consider a higher-end GPU for better results.

Model Size

7.62B

Device VRAM

18 GB

Bandwidth

150 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Qwen 2.5 Coder 7B Instruct performance at a different quality level on Apple M3 Pro (18GB Unified).

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q4_K_M15 tok/s395ms✓ YesAcceptableestimated

Notes

Q4_K_M

Coding model. Usable for Cursor/Continue. Slower than M4 Pro.

About Qwen 2.5 Coder 7B Instruct

Qwen 2.5 Coder 7B Instruct (7.62B) is a coding, ai coding model. Specialized coding model optimized for AI-assisted development.

View all Qwen 2.5 Coder 7B 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: 2026-03-15