What GPU do I need to run moonshotai/Moonlight-16B-A3B-Instruct?
16.0B parameters, published in BF16. View on Hugging Face
Moonlight-16B-A3B-Instruct is published by moonshotai on Hugging Face, with 62,167 downloads and 203 likes to date. It's a DeepseekV3ForCausalLM model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Moonlight-16B-A3B-Instruct at its published (BF16) precision: 1× A40 on runpod, at $0.440/hr per GPU ($0.440/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More moonshotai models
- Kimi-VL-A3B-Instruct (16.4B, BF16)
- Kimi-Linear-48B-A3B-Instruct (49.1B, BF16)
- Kimi-K2-Instruct (1026.4B, F8_E4M3)
- Kimi-K2-Instruct-0905 (1026.5B, F8_E4M3)
- Moonlight-16B-A3B (16.0B, BF16)
- Kimi-K2-Base (1026.5B, F8_E4M3)
