RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM2 360M run on the Mac M4 Max 128GB?

Yes. At 8K context the best fit is F16, using about 1.5 GB of the 96.0 GB usable on the Mac M4 Max 128GB. Estimated speed ceiling: ~753 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •0.9 GB Fits1.0 GB Fits2497
3-bit (Q3_K_M) •0.9 GB Fits1.0 GB Fits2327
4-bit (Q4_K_M) •0.9 GB Fits1.1 GB Fits2018
5-bit (Q5_K_M) •0.9 GB Fits1.1 GB Fits1883
6-bit (Q6_K) •1.0 GB Fits1.1 GB Fits1486
8-bit (Q8_0) •1.0 GB Fits1.2 GB Fits1413
16-bit (F16/BF16) •1.3 GB Fits1.5 GB Fits753

• real GGUF file size from mradermacher/SmolLM2-360M-GGUF. Speed is a bandwidth ceiling (546 GB/s), not a benchmark. Methodology.

More

SmolLM2 360M on every GPU and Mac · Every model that runs on the Mac M4 Max 128GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (HuggingFaceTB/SmolLM2-360M), Apple specs. Data as of 2026-11-17.