RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Moonlight 16B A3B Instruct run on the RTX 3070?

Yes. At 8K context the best fit is Q2_K, using about 7.1 GB of the 7.6 GB usable on the RTX 3070. Estimated speed ceiling: ~362 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •7.0 GB Tight7.1 GB Tight362
3-bit (Q3_K_M) •8.5 GB No8.7 GB No—
4-bit (Q4_K_M) •10.6 GB No10.8 GB No—
5-bit (Q5_K_M) •12.0 GB No12.2 GB No—
6-bit (Q6_K) •14.1 GB No14.2 GB No—
8-bit (Q8_0) •16.6 GB No16.8 GB No—
16-bit (F16/BF16)30.6 GB No30.7 GB No—

• real GGUF file size from mmnga/Moonlight-16B-A3B-Instruct-gguf. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.

More

Moonlight 16B A3B Instruct on every GPU and Mac · Every model that runs on the RTX 3070 · Other models that fit 8 GB VRAM · Try other settings in the calculator

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