RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3 4B run on the Mac M3 24GB?

Yes. At 8K context the best fit is F16, using about 9.3 GB of the 16.1 GB usable on the Mac M3 24GB. Estimated speed ceiling: ~12 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.7 GB Fits3.2 GB Fits6.6 GB Fits66
3-bit (Q3_K_M)3.1 GB Fits3.6 GB Fits7.0 GB Fits51
4-bit (Q4_K_M) •3.6 GB Fits4.1 GB Fits7.5 GB Fits40
5-bit (Q5_K_M) •3.9 GB Fits4.5 GB Fits7.9 GB Fits35
6-bit (Q6_K) •4.3 GB Fits4.9 GB Fits8.3 GB Fits30
8-bit (Q8_0) •5.2 GB Fits5.8 GB Fits9.2 GB Fits23
16-bit (F16/BF16)8.7 GB Fits9.3 GB Fits12.7 GB Fits12

• real GGUF file size from Qwen/Qwen3-4B-GGUF. Speed is a bandwidth ceiling (100 GB/s), not a benchmark. Methodology.

More

Qwen3 4B on every GPU and Mac · Every model that runs on the Mac M3 24GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen3-4B), Apple specs. Model data last checked 2026-11-17; refreshed hourly.