RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can WeVisOne VL 4B run on the Mac M1 Pro 32GB?

Yes. At 8K context the best fit is F16, using about 10.0 GB of the 21.4 GB usable on the Mac M1 Pro 32GB. Estimated speed ceiling: ~23 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.9 GB Fits3.5 GB Fits6.9 GB Fits20.4 GB Tight111
3-bit (Q3_K_M) •3.3 GB Fits3.9 GB Fits7.3 GB Fits20.8 GB Tight89
4-bit (Q4_K_M) •3.8 GB Fits4.3 GB Fits7.7 GB Fits21.2 GB Tight74
5-bit (Q5_K_M) •4.2 GB Fits4.8 GB Fits8.1 GB Fits21.6 GB No63
6-bit (Q6_K) •4.6 GB Fits5.2 GB Fits8.6 GB Fits22.1 GB No55
8-bit (Q8_0) •5.6 GB Fits6.2 GB Fits9.6 GB Fits23.1 GB No43
16-bit (F16/BF16) •9.5 GB Fits10.0 GB Fits13.4 GB Fits26.9 GB No23

• real GGUF file size from mradermacher/WeVisOne-VL-4B-GGUF. Speed is a bandwidth ceiling (200 GB/s), not a benchmark. Methodology.

More

WeVisOne VL 4B on every GPU and Mac · Every model that runs on the Mac M1 Pro 32GB · Apple Silicon guide · Try other settings in the calculator

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