Can Moonlight 16B A3B Instruct run on the A100 40GB?
Yes. At 8K context the best fit is F16, using about 30.7 GB of the 38.0 GB usable on the A100 40GB. Estimated speed ceiling: ~259 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 | 1258 |
| 3-bit (Q3_K_M) • | 8.5 GB Fits | 8.7 GB Fits | 998 |
| 4-bit (Q4_K_M) • | 10.6 GB Fits | 10.8 GB Fits | 785 |
| 5-bit (Q5_K_M) • | 12.0 GB Fits | 12.2 GB Fits | 687 |
| 6-bit (Q6_K) • | 14.1 GB Fits | 14.2 GB Fits | 580 |
| 8-bit (Q8_0) • | 16.6 GB Fits | 16.8 GB Fits | 487 |
| 16-bit (F16/BF16) | 30.6 GB Fits | 30.7 GB Fits | 259 |
• real GGUF file size from mmnga/Moonlight-16B-A3B-Instruct-gguf. Speed is a bandwidth ceiling (1555 GB/s), not a benchmark. Methodology.
More
Moonlight 16B A3B Instruct on every GPU and Mac · Every model that runs on the A100 40GB · Other models that fit 48 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.