RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek OCR 2 run on the Mac M2 Max 96GB?

Yes. At 8K context the best fit is F16, using about 6.6 GB of the 72.0 GB usable on the Mac M2 Max 96GB. Estimated speed ceiling: ~193 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.1 GB Fits2.3 GB Fits893
3-bit (Q3_K_M)2.4 GB Fits2.7 GB Fits685
4-bit (Q4_K_M) •2.7 GB Fits2.9 GB Fits582
5-bit (Q5_K_M)3.1 GB Fits3.4 GB Fits470
6-bit (Q6_K)3.5 GB Fits3.7 GB Fits409
8-bit (Q8_0) •3.8 GB Fits4.0 GB Fits363
16-bit (F16/BF16) •6.4 GB Fits6.6 GB Fits193

• real GGUF file size from sabafallah/DeepSeek-OCR-2-GGUF. Speed is a bandwidth ceiling (400 GB/s), not a benchmark. Methodology.

More

DeepSeek OCR 2 on every GPU and Mac · Every model that runs on the Mac M2 Max 96GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/DeepSeek-OCR-2), Apple specs. Data as of 2026-11-17.