RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Moonlight 16B A3B Instruct run on the 2x RTX 4090?

Yes. At 8K context the best fit is F16, using about 30.7 GB of the 45.6 GB usable on the 2x RTX 4090. Estimated speed ceiling: ~168 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •7.0 GB Fits7.1 GB Fits816
3-bit (Q3_K_M) •8.5 GB Fits8.7 GB Fits647
4-bit (Q4_K_M) •10.6 GB Fits10.8 GB Fits509
5-bit (Q5_K_M) •12.0 GB Fits12.2 GB Fits445
6-bit (Q6_K) •14.1 GB Fits14.2 GB Fits376
8-bit (Q8_0) •16.6 GB Fits16.8 GB Fits316
16-bit (F16/BF16)30.6 GB Fits30.7 GB Fits168

• real GGUF file size from mmnga/Moonlight-16B-A3B-Instruct-gguf. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.

More

Moonlight 16B A3B Instruct on every GPU and Mac · Every model that runs on the 2x RTX 4090 · Try other settings in the calculator

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