OwnRig

DeepSeek R1 Distill Qwen 7B on Apple M3 Pro (18GB Unified)

Apple M3 Pro (18GB Unified) can run DeepSeek R1 Distill Qwen 7B at 14 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 DeepSeek R1 Distill Qwen 7B performance at a different quality level on Apple M3 Pro (18GB Unified).

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q4_K_M14 tok/s410ms✓ YesAcceptableestimated

Notes

Q4_K_M

Reasoning model. Slower on M3 Pro but usable.

About DeepSeek R1 Distill Qwen 7B

DeepSeek R1 Distill Qwen 7B (7.62B) is a reasoning, chat model. Compact distilled reasoning model for chat and inference.

View all DeepSeek R1 Distill Qwen 7B 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