RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Moonlight 16B A3B Instruct run on the Mac M3 Ultra 256GB?

Yes. At 8K context the best fit is F16, using about 30.7 GB of the 192 GB usable on the Mac M3 Ultra 256GB. Estimated speed ceiling: ~137 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •7.0 GB Fits7.1 GB Fits663
3-bit (Q3_K_M) •8.5 GB Fits8.7 GB Fits526
4-bit (Q4_K_M) •10.6 GB Fits10.8 GB Fits413
5-bit (Q5_K_M) •12.0 GB Fits12.2 GB Fits362
6-bit (Q6_K) •14.1 GB Fits14.2 GB Fits305
8-bit (Q8_0) •16.6 GB Fits16.8 GB Fits257
16-bit (F16/BF16)30.6 GB Fits30.7 GB Fits137

• real GGUF file size from mmnga/Moonlight-16B-A3B-Instruct-gguf. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.

More

Moonlight 16B A3B Instruct on every GPU and Mac · Every model that runs on the Mac M3 Ultra 256GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (moonshotai/Moonlight-16B-A3B-Instruct), Apple specs. Model data last checked 2026-11-17; refreshed hourly.