Moonlight 16B-A3B Instruct on NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Can the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB) run Moonlight 16B-A3B Instruct?

Yes, it runs great

Runs great. At Q5_K_M it needs about 13.5 GB of 16.0 GB usable, with an estimated speed of 74.8 tok/s.

Best quant: Q5_K_M
Generation speed: 74.8 tok/s
Prompt processing: 5,760 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 8K

Best app to run it on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

On Linux

Docker Model Runner

Command line + local API · runs on llama.cpp, vLLM

Handy if you already work in Docker.

docker model run hf.co/moonshotai/Moonlight-16B-A3B-Instruct

Text Generation WebUI

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Moonlight 16B-A3B Instruct

Original weights · Hugging Face

Full-precision files from Moonshot AI, for fine-tuning, vLLM, Transformers.

huggingface.co/moonshotai/Moonlight-16B-A3B-Instruct (opens in a new tab)

No sign-in needed.

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q5_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	20.1 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	75.1 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	8.5 GB	16.0 GB	124 tok/s	Runs great	32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	10.0 GB	16.0 GB	105 tok/s	Runs great	38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	11.9 GB	16.0 GB	86.9 tok/s	Runs great	43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	13.5 GB	16.0 GB	74.8 tok/s	Runs great	44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	15.2 GB	16.0 GB	65.1 tok/s	Runs welltight fit	45Fair quality (C) · 45 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	19.1 GB	16.0 GB	42.9 tok/s	Slowfar over GPU memory limit	46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	34.1 GB	16.0 GB	—	Won't run	46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q8_0 · 104 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 112 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 117 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q5_K_M · 113 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) Q5_K_M · 62.2 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Ti 16GB Q5_K_M · 72.6 tok/s · Runs great

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.