OwnRig

Mistral Small 24B Instruct on Apple M4 Max (64GB Unified)

Apple M4 Max (64GB Unified) handles Mistral Small 24B Instruct well at 22 tok/s at Q5_K_M. A solid choice for this model.

Model Size

24B

Device VRAM

64 GB

Bandwidth

546 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows Mistral Small 24B Instruct performance at a different quality level on Apple M4 Max (64GB Unified).

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q5_K_M22 tok/s400ms✓ YesGoodestimated

Notes

Q5_K_M

Q5 fits in 64GB. Good quality on Mac.

About Mistral Small 24B Instruct

Mistral Small 24B Instruct (24B) is a chat, coding, reasoning model. Mistral's efficient 24B model with strong chat, coding, and reasoning.

View all Mistral Small 24B Instruct hardware options →

About Apple M4 Max (64GB Unified)

Apple M4 Max (64GB Unified) has 64 GB at 546 GB/s. Available in MacBook Pro 16", Mac Studio.

See all models Apple M4 Max (64GB Unified) can run →

Source: MLX performance estimates (2026-03-01)

Data last updated: 2026-03-15