MiniCPM-V 4.7 35B-A3B on ZhaoXin KX-U6580 NAS (64 GB)

Can the ZhaoXin KX-U6580 NAS (64 GB) run MiniCPM-V 4.7 35B-A3B?

Yes, but slowly

Slow. At Q6_K it needs about 34.0 GB of 54.4 GB usable, with an estimated speed of 4.1 tok/s.

Best quant: Q6_K
Generation speed: 4.1 tok/s
Prompt processing: 8.3 tok/s
First token (1K prompt): 122.9 s
Largest safe context: 256K

Best app to run it on the ZhaoXin KX-U6580 NAS (64 GB)

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Usually the first to support new model architectures.

llama-server -hf openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q6_K

Ollama Runs the Hugging Face GGUF with ollama run hf.co/…
KoboldCpp

Want an agent? MiniCPM-V 4.7 35B-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, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download MiniCPM-V 4.7 35B-A3B

Recommended for the ZhaoXin KX-U6580 NAS (64 GB): Q6_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q6_K file (opens in a new tab)

huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf (opens in a new tab)

ollama run hf.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q6_K

Original weights · Hugging Face

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

huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/OpenBMB/MiniCPM-V (opens in a new tab)

git clone https://github.com/OpenBMB/MiniCPM-V

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_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 Slow: How well it runs on the ZhaoXin KX-U6580 NAS (64 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.	41.6 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); 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.	4.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	14.4 / 15
Match score	85.8 / 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 ZhaoXin KX-U6580 NAS (64 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	19.2 GB	54.4 GB	9.7 tok/s	Slow	65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	22.4 GB	54.4 GB	7.6 tok/s	Slow	78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (IQ3_M) (opens in a new tab)
`Q4_K_M`	26.6 GB	54.4 GB	5.9 tok/s	Slow	88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	30.1 GB	54.4 GB	4.9 tok/s	Slow	90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	34.0 GB	54.4 GB	4.1 tok/s	Slow	92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	42.4 GB	54.4 GB	3.1 tok/s	Slow	93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	75.5 GB	54.4 GB	—	Won't run	93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) 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

93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell F16 · 98.2 tok/s · Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q6_K · 72.3 tok/s · Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q6_K · 90.1 tok/s · Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q5_K_M · 62.2 tok/s · Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 179 tok/s · Runs well (tight fit)
93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) F16 · 51.3 tok/s · Runs great

Quick answers

How much memory does MiniCPM-V 4.7 35B-A3B need on the ZhaoXin KX-U6580 NAS 64GB?

At Q6_K it needs about 34.0 GB. The ZhaoXin KX-U6580 NAS 64GB has 54.4 GB usable.

How fast is MiniCPM-V 4.7 35B-A3B on the ZhaoXin KX-U6580 NAS 64GB?

About 4.1 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of MiniCPM-V 4.7 35B-A3B should I use on the ZhaoXin KX-U6580 NAS 64GB?

Q6_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.