on

Can the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB) run Hunyuan Hy-Memory 30B-A3B?

59Good quality (B) · 59 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well (tight fit)

Runs well (tight fit). At Q2_K it needs about 14.7 GB of 16.0 GB usable, with an estimated speed of 124 tok/s.

Best quant
Q2_K
Generation speed
124 tok/s
Prompt processing
5,760 tok/s
First token (1K prompt)
0.3 s
Largest safe context
20K

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

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open Hunyuan Hy-Memory 30B-A3B in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

Want an agent? Hunyuan Hy-Memory 30B-A3B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 Hunyuan Hy-Memory 30B-A3B

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF (opens in a new tab)

ollama run hf.co/tencent/Hy-Memory-30B-A3B-GGUF

Original weights · Hugging Face

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

huggingface.co/tencent/Hy-Memory-30B-A3B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Tencent. The weights themselves download from Hugging Face.

github.com/Tencent-Hunyuan/Hy-Memory (opens in a new tab)

git clone https://github.com/Tencent-Hunyuan/Hy-Memory

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

How it’s rated

Quality 59Good quality (B) · 59 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q2_K, 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 welltight fit
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.26.8 / 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.24.0 / 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 score80.8 / 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 14.7 GB 16.0 GB 124 tok/s Runs welltight fit 59Good quality (B) · 59 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q3_K_M 17.4 GB 16.0 GB 89.1 tok/s Runs wellover GPU memory limit 71Great quality (A) · 71 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 21.0 GB 16.0 GB — Won't run 80Great quality (A) · 80 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 24.0 GB 16.0 GB — Won't run 82Great quality (A) · 82 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q6_K 27.3 GB 16.0 GB — Won't run 84Great quality (A) · 84 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 34.5 GB 16.0 GB — Won't run 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 62.8 GB 16.0 GB — Won't run 85Excellent quality (A+) · 85 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (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

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.

Was this page helpful?