RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 3.2 3B run on the Mac M4 32GB?

Yes. At 8K context the best fit is F16, using about 7.5 GB of the 21.4 GB usable on the Mac M4 32GB. Estimated speed ceiling: ~19 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.5 GB Fits2.9 GB Fits5.5 GB Fits16.0 GB Fits80
3-bit (Q3_K_M) •2.8 GB Fits3.2 GB Fits5.9 GB Fits16.4 GB Fits65
4-bit (Q4_K_M) •3.2 GB Fits3.6 GB Fits6.2 GB Fits16.7 GB Fits54
5-bit (Q5_K_M) •3.5 GB Fits3.9 GB Fits6.6 GB Fits17.1 GB Fits46
6-bit (Q6_K) •3.8 GB Fits4.3 GB Fits6.9 GB Fits17.4 GB Fits40
8-bit (Q8_0) •4.7 GB Fits5.1 GB Fits7.7 GB Fits18.2 GB Fits31
16-bit (F16/BF16)7.1 GB Fits7.5 GB Fits10.1 GB Fits20.6 GB Tight19

• real GGUF file size from QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF. Speed is a bandwidth ceiling (120 GB/s), not a benchmark. Methodology.

More

Llama 3.2 3B on every GPU and Mac · Every model that runs on the Mac M4 32GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (meta-llama/Llama-3.2-3B), Apple specs. Data as of 2026-11-17.