OwnRig

DeepSeek V3 on Apple M4 Max (36GB Unified)

Apple M4 Max (36GB Unified) cannot run DeepSeek V3 at any quantization level. The 36 GB of VRAM is insufficient.

Model Size

671B

Device VRAM

36 GB

Bandwidth

546 GB/s

Quantizations Tested

1

Performance by Quantization

Each row shows DeepSeek V3 performance at a different quality level on Apple M4 Max (36GB Unified).

QuantizationSpeedTTFTFits in VRAMRatingConfidence
Q2_K✗ OffloadNot Viableestimated

Notes

Q2_K

671B MoE model requires 115GB+ at Q2_K. 36GB insufficient. Would need M4 Max 128GB.

About DeepSeek V3

DeepSeek V3 (671B) is a chat, coding, ai coding, reasoning, multi-purpose model. Massive MoE model rivaling GPT-4 class. Only ~37B parameters active per token despite 671B total. Requires multi-GPU or very large unified memory (128GB+ Apple Silicon at Q2/Q3). Not for casual home use — included for completeness and to show what the high end looks like.

View all DeepSeek V3 hardware options →

About Apple M4 Max (36GB Unified)

Apple M4 Max (36GB Unified) has 36 GB at 546 GB/s. Available in MacBook Pro 16", Mac Studio.

See all models Apple M4 Max (36GB Unified) can run →

Source: MLX performance estimates (2026-03-15)

Data last updated: 2026-03-15