RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM2 1.7B run on the Mac M2 Max 96GB?

Yes. At 8K context the best fit is F16, using about 5.2 GB of the 72.0 GB usable on the Mac M2 Max 96GB. Estimated speed ceiling: ~117 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.8 GB Fits2.6 GB Fits623
3-bit (Q3_K_M)2.0 GB Fits2.8 GB Fits478
4-bit (Q4_K_M) •2.3 GB Fits3.0 GB Fits370
5-bit (Q5_K_M)2.4 GB Fits3.1 GB Fits328
6-bit (Q6_K)2.6 GB Fits3.3 GB Fits285
8-bit (Q8_0) •3.0 GB Fits3.7 GB Fits216
16-bit (F16/BF16)4.4 GB Fits5.2 GB Fits117

• real GGUF file size from namindu94/SinhalaLLM-1.7B. Speed is a bandwidth ceiling (400 GB/s), not a benchmark. Methodology.

More

SmolLM2 1.7B 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 (HuggingFaceTB/SmolLM2-1.7B), Apple specs. Data as of 2026-11-17.