RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM2 1.7B run on the Mac M4 Pro 24GB?

Yes. At 8K context the best fit is F16, using about 5.2 GB of the 16.1 GB usable on the Mac M4 Pro 24GB. Estimated speed ceiling: ~80 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.8 GB Fits2.6 GB Fits425
3-bit (Q3_K_M)2.0 GB Fits2.8 GB Fits326
4-bit (Q4_K_M) •2.3 GB Fits3.0 GB Fits253
5-bit (Q5_K_M)2.4 GB Fits3.1 GB Fits224
6-bit (Q6_K)2.6 GB Fits3.3 GB Fits195
8-bit (Q8_0) •3.0 GB Fits3.7 GB Fits147
16-bit (F16/BF16)4.4 GB Fits5.2 GB Fits80

• real GGUF file size from namindu94/SinhalaLLM-1.7B. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.

More

SmolLM2 1.7B on every GPU and Mac · Every model that runs on the Mac M4 Pro 24GB · 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.