Can Moonlight 16B A3B Instruct run on the DGX Spark?
Yes. At 8K context the best fit is F16, using about 30.7 GB of the 109 GB usable on the DGX Spark. Estimated speed ceiling: ~46 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | Max tok/s (est., 8K) |
|---|---|---|---|
| 2-bit (Q2_K) • | 7.0 GB Fits | 7.1 GB Fits | 221 |
| 3-bit (Q3_K_M) • | 8.5 GB Fits | 8.7 GB Fits | 175 |
| 4-bit (Q4_K_M) • | 10.6 GB Fits | 10.8 GB Fits | 138 |
| 5-bit (Q5_K_M) • | 12.0 GB Fits | 12.2 GB Fits | 121 |
| 6-bit (Q6_K) • | 14.1 GB Fits | 14.2 GB Fits | 102 |
| 8-bit (Q8_0) • | 16.6 GB Fits | 16.8 GB Fits | 86 |
| 16-bit (F16/BF16) | 30.6 GB Fits | 30.7 GB Fits | 46 |
• real GGUF file size from mmnga/Moonlight-16B-A3B-Instruct-gguf. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.
More
Moonlight 16B A3B Instruct on every GPU and Mac · Every model that runs on the DGX Spark · Other models that fit 64 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.