Topton N25 14-bay dual-10GbE NAS motherboard (Core Ultra 5 225H / 7 255H / 9 285H)

Products · · NAS

Topton N25 14-bay dual-10GbE NAS motherboard (Core Ultra 5 225H / 7 255H / 9 285H)

Chips
Intel Core Ultra 5 225H or Intel Core Ultra 7 255H / 9 285H
Memory (RAM)
32 or 64 GB
Launch price
$791
Released
2026

Product page (opens in a new tab) Full AI report

Configurations

Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.

Configuration Memory Usable for AI Bandwidth LLMs that run well Launch price
Intel Core Ultra 5 225H · Intel Core Ultra 5 225H 32.0 GB 18.2 GB 102 GB/s 386 of 622 $791
Intel Core Ultra 7 255H / 9 285H · Intel Core Ultra 7 255H / 9 285H 32.0 GB 18.2 GB 102 GB/s 386 of 622 —
Intel Core Ultra 5 225H · Intel Core Ultra 5 225H 64.0 GB 36.5 GB 102 GB/s 397 of 622 —
Intel Core Ultra 7 255H / 9 285H · Intel Core Ultra 7 255H / 9 285H 64.0 GB 36.5 GB 102 GB/s 397 of 622 —

Specifications 32.0 GB configuration

MakerTopton
TypeNAS
ProcessorIntel Core Ultra 5 225H NAS (32 GB) · Intel Core Ultra 5 225H
Memory (RAM)32.0 GB
Usable for AI models18.2 GB
Memory bandwidth102 GB/s
FP16 compute8.0 TFLOPS
Runs models onGPU (Vulkan)
Drive bays12x SATA III (3x SFF-8087) + 2x M.2 2280 NVMe (PCIe 4.0 x4 / 3.0 x4)
NAS systemSold without an OS
Containers (Docker)Yes
Virtual machinesYes
Memory upgradeLPDDR5 8400 MHz (soldered) · up to 64.0 GB per the maker · non-ECC
Graphics card optionsPCIe: 1x PCIe 4.0 x8 slot; maker says it supports a graphics card. External GPU: 2x Thunderbolt 4 / USB4 ports; eGPU use not documented by the maker.
NotesIntel Core Ultra 5 225H, Ultra 7 255H or Ultra 9 285H (Arrow Lake-H). 32 or 64 GB of fast soldered LPDDR5, Arc 140T iGPU, a PCIe 4.0 x8 slot the maker says takes a graphics card, and Thunderbolt 4: runs 14B-class quantized models on iGPU/CPU and larger with a GPU.
Product pagewww.toptonpc.com (opens in a new tab)

Running AI on the Topton N25 14-bay dual-10GbE NAS motherboard (Core Ultra 5 225H / 7 255H / 9 285H)

Yes, it runs AI models on the NAS itself. Models run on its GPU (Vulkan), and this configuration leaves about 18.2 GB for them after the NAS system and its storage services. The grades below assume the NAS isn’t busy with backups or media work at the same time. More memory is the upgrade that matters most: see the configurations.

Apps you can install to run models

AppHow it installs
Ollama In a container (Docker)
Open WebUI In a container (Docker)

Apps that run LLMs on a NAS, with their container images

Best LLMs for the Topton N25 14-bay dual-10GbE NAS motherboard (Core Ultra 5 225H / 7 255H / 9 285H) 32.0 GB

Quality Model Quant Memory Speed Runs
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle Q4_K_M 18.2 GB 29.0 tok/s Runs welltight fit
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B)Zhipu AI Q3_K_M 17.8 GB 45.0 tok/s Runs welltight fit
71Great quality (A) · 71 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy-Memory 30B-A3BTencent Q3_K_M 17.6 GB 45.0 tok/s Runs welltight fit
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B)KRAFTON Q3_K_M 16.2 GB 32.8 tok/s Runs welltight fit
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2BLiquid AI Q4_K_M 16.8 GB 42.7 tok/s Runs welltight fit
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20BOpenAI MXFP4 14.2 GB 32.4 tok/s Runs great
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B)DeepGrove Q4_K_M 14.5 GB 64.3 tok/s Runs great
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. DiffusionGemma 26B-A4B ITGoogle Q4_K_M 18.2 GB 27.7 tok/s Runs welltight fit
67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. North Mini Code 1.0 (30B-A3B)Cohere Q3_K_M 17.3 GB 45.0 tok/s Runs welltight fit
67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Nemotron Cascade 2 30B-A3BNVIDIA Q3_K_M 17.6 GB 39.4 tok/s Runs welltight fit

Best Image models for the Topton N25 14-bay dual-10GbE NAS motherboard (Core Ultra 5 225H / 7 255H / 9 285H) 32.0 GB

Quality Model Quant Memory Speed Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 4BBlack Forest Labs FP8 10.2 GB 9.3 s Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) FP8 12.6 GB 23 s Runs well
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs FP8 12.4 GB 53 s Slow
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu FP8 14.5 GB 30 s Runs well
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs FP8 11.7 GB 18 s Runs wellencoder unloaded after use
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP8 15.7 GB 42 s Slowtight fit · encoder unloaded after use

Best Video models for the Topton N25 14-bay dual-10GbE NAS motherboard (Core Ultra 5 225H / 7 255H / 9 285H) 32.0 GB

Quality Model Quant Memory Speed Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 2BLightricks FP8 10.8 GB 3.9 min Runs great
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. HY-OmniWeaving (8.3B, unified video)Tencent FP8 15.7 GB 86.5 min Very slowtight fit · encoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. CogVideoX 5BZhipu AI FP8 14.3 GB 28.0 min Slow
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. CogVideoX 5B I2VZhipu AI FP8 14.9 GB 28.0 min Slow
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. Kandinsky 6.0 Video Lite (3B, video + audio)Sber AI FP16 14.7 GB 56.2 min Very slowencoder unloaded after use

Best Decision models for the Topton N25 14-bay dual-10GbE NAS motherboard (Core Ultra 5 225H / 7 255H / 9 285H) 32.0 GB

Quality Model Quant Memory Speed Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5Jina AI F16 3.5 GB 80 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3Jina AI F16 3.5 GB 80 ms Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. FRIDA-DecisionsSber AI F16 2.4 GB 51 ms Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. GLiNER2.5 DecideFastino F16 1.7 GB 32 ms Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 0.6BAlibaba F16 3.5 GB 80 ms Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 86MMeta F16 1.2 GB 36 ms Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-base v2Mixedbread F16 3.1 GB 66 ms Runs great
82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-large v2Mixedbread Q8_0 3.8 GB 170 ms Runs well

Spec sources

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?