RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Nemotron 3.5 Parse run on the Mac M3 Pro 36GB?

Yes. At 8K context the best fit is F16, using about 1.9 GB of the 24.1 GB usable on the Mac M3 Pro 36GB. Estimated speed ceiling: ~115 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)0.8 GB Fits0.9 GB Fits634
3-bit (Q3_K_M)0.9 GB Fits1.0 GB Fits487
4-bit (Q4_K_M)1.0 GB Fits1.1 GB Fits389
5-bit (Q5_K_M)1.0 GB Fits1.1 GB Fits334
6-bit (Q6_K)1.1 GB Fits1.2 GB Fits290
8-bit (Q8_0) •1.4 GB Fits1.5 GB Fits173
16-bit (F16/BF16) •1.8 GB Fits1.9 GB Fits115

• real GGUF file size from SkyContact/Nemotron-3.5-Parse-GGUF. Speed is a bandwidth ceiling (150 GB/s), not a benchmark. Methodology.

More

Nemotron 3.5 Parse on every GPU and Mac · Every model that runs on the Mac M3 Pro 36GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (nvidia/Nemotron-3.5-Parse), Apple specs. Data as of 2026-11-17.