on

Can the Intel Xeon D-1600 series NAS (128 GB) run Kimi-VL A3B Thinking 2506?

50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well

Runs well. At Q3_K_M it needs about 17.9 GB of 113 GB usable, with an estimated speed of 12.2 tok/s.

Best quant
Q3_K_M
Generation speed
12.2 tok/s
Prompt processing
37.5 tok/s
First token (1K prompt)
27.3 s
Largest safe context
128K

Best app to run it on the Intel Xeon D-1600 series NAS (128 GB)

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

  • Usually the first to support new model architectures.
llama-server -hf ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF:Q3_K_M

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 Kimi-VL A3B Thinking 2506

Quantized files · GGUF

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

huggingface.co/ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF (opens in a new tab)

ollama run hf.co/ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF

Original weights · Hugging Face

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

huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506 (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q3_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 well
How well it runs on the Intel Xeon D-1600 series NAS (128 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.22.7 / 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.8.3 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.3.7 / 15
Match score59.6 / 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 Intel Xeon D-1600 series NAS (128 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 16.4 GB 113 GB 15.4 tok/s Runs well 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q3_K_M 17.9 GB 113 GB 12.2 tok/s Runs well 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q4_K_M 19.9 GB 113 GB 9.5 tok/s Slow 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 21.5 GB 113 GB 7.9 tok/s Slow 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q6_K 23.3 GB 113 GB 6.7 tok/s Slow 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q8_0 27.3 GB 113 GB 4.9 tok/s Slow 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 42.7 GB 113 GB 2.3 tok/s Very slow 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (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

Quick answers

How much memory does Kimi-VL A3B Thinking 2506 need on the Intel Xeon D-1600 series NAS 128GB?

At Q3_K_M it needs about 17.9 GB. The Intel Xeon D-1600 series NAS 128GB has 113 GB usable.

How fast is Kimi-VL A3B Thinking 2506 on the Intel Xeon D-1600 series NAS 128GB?

About 12.2 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Kimi-VL A3B Thinking 2506 should I use on the Intel Xeon D-1600 series NAS 128GB?

Q3_K_M. 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.

Was this page helpful?