RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek vl2 tiny run on the Mac M4 Pro 24GB?

Yes. At 8K context the best fit is F16, using about 7.4 GB of the 16.1 GB usable on the Mac M4 Pro 24GB. Estimated speed ceiling: ~116 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.1 GB Fits619
3-bit (Q3_K_M)2.4 GB Fits475
4-bit (Q4_K_M)2.8 GB Fits380
5-bit (Q5_K_M)3.1 GB Fits326
6-bit (Q6_K)3.5 GB Fits283
8-bit (Q8_0)4.2 GB Fits219
16-bit (F16/BF16)7.2 GB Fits116

• real GGUF file size. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.

More

deepseek vl2 tiny 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 (deepseek-ai/deepseek-vl2-tiny), Apple specs. Data as of 2026-11-17.