OwnRig

InternLM 2.5 7B Chat on Apple M3 Pro (18GB Unified)

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

Model Size

7.74B

Device VRAM

18 GB

Bandwidth

150 GB/s

Quantizations Tested

1

Performance by Quantization

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

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q4_K_M15 tok/s390ms✓ YesAcceptableestimated

Notes

Q4_K_M

Bandwidth-limited. Acceptable for multilingual chat.

About InternLM 2.5 7B Chat

InternLM 2.5 7B Chat (7.74B) is a chat, coding, reasoning model. Shanghai AI Lab's efficient 7B model with strong coding and reasoning.

View all InternLM 2.5 7B Chat 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