Can I run Moonlight-16B-A3B on an RTX 6000 Ada?

Yes

Its published weights (31.9 GB) fit in the 43.2 GB an RTX 6000 Ada can use, with room for ≈ 8K tokens of context.

Full analysis of Moonlight-16B-A3B Everything that runs on RTX 6000 Ada Get the weights on Hugging Face

hf download moonshotai/Moonlight-16B-A3B

Files and context on RTX 6000 Ada

Each file of Moonlight-16B-A3B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On RTX 6000 Ada	Context (16-bit)	Context (8-bit)
As published	31.9 GB	Fits	8K	8K
4-bit (estimate)	8.98 GB	Fits	8K	8K

Moonlight-16B-A3B on other hardware

NVIDIA H100Yes
RTX 5090Probably, at 4-bit
RTX 4090Probably, at 4-bit
RTX 3090Probably, at 4-bit
RTX 5060 Ti 16 GBProbably, at 4-bit
RTX 3060 12 GBProbably, at 4-bit
RTX 4060No
RTX 6000 AdaYes
Mac with 32 GBProbably, at 4-bit
Mac with 64 GBYes
Mac with 128 GBYes

Popular models that run on RTX 6000 Ada

Qwen3-0.6BQwen · 752M
Qwen3-VL-8B-InstructQwen · 8.77B
gpt2openai-community · 137M
Qwen3-8BQwen · 8.19B
Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth · 30.5B
Qwen2.5-7B-InstructQwen · 7.62B
Qwen3.5-9BQwen · 9.65B
Qwen2.5-0.5B-InstructQwen · 494M

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.