RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Moonlight 16B A3B Instruct run on the Mac M2 Ultra 192GB?

Yes. At 8K context the best fit is F16, using about 30.7 GB of the 144 GB usable on the Mac M2 Ultra 192GB. Estimated speed ceiling: ~133 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •7.0 GB Fits7.1 GB Fits647
3-bit (Q3_K_M) •8.5 GB Fits8.7 GB Fits514
4-bit (Q4_K_M) •10.6 GB Fits10.8 GB Fits404
5-bit (Q5_K_M) •12.0 GB Fits12.2 GB Fits353
6-bit (Q6_K) •14.1 GB Fits14.2 GB Fits298
8-bit (Q8_0) •16.6 GB Fits16.8 GB Fits251
16-bit (F16/BF16)30.6 GB Fits30.7 GB Fits133

• real GGUF file size from mmnga/Moonlight-16B-A3B-Instruct-gguf. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.

More

Moonlight 16B A3B Instruct on every GPU and Mac · Every model that runs on the Mac M2 Ultra 192GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (moonshotai/Moonlight-16B-A3B-Instruct), Apple specs. Data as of 2026-11-17.