OwnRig

Llama 3.1 8B Instruct on Apple M4 Pro (24GB Unified)

Apple M4 Pro (24GB Unified) handles Llama 3.1 8B Instruct well at 32 tok/s at Q8_0. A solid choice for this model.

Model Size

8.03B

Device VRAM

24 GB

Bandwidth

273 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Llama 3.1 8B Instruct performance at a different quality level on Apple M4 Pro (24GB Unified).

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q8_032 tok/s250ms✓ YesGoodestimated

Notes

Q8_0

Unified memory means no PCIe bottleneck, but lower bandwidth (273 GB/s) limits throughput vs discrete GPUs.

About Llama 3.1 8B Instruct

Llama 3.1 8B Instruct (8.03B) is a chat, coding, ai coding, reasoning, multi-purpose model. Best-in-class 8B model. Strong general capabilities with excellent coding support. The go-to small model for local inference — fast, accurate, and well-supported across all inference engines.

View all Llama 3.1 8B Instruct hardware options →

About Apple M4 Pro (24GB Unified)

Apple M4 Pro (24GB Unified) has 24 GB at 273 GB/s. Available in MacBook Pro 14", MacBook Pro 16", Mac Mini.

See all models Apple M4 Pro (24GB Unified) can run →

Source: MLX benchmark results (2026-01-15)

Data last updated: 2026-03-01