Products · UGREEN · NAS
UGREEN NASync DXP4800 Pro
- Processor
- Intel Core i3-1215U / i3-1315U
- Memory (RAM)
- 8 or 96 GB
- Launch price
- $680
- Released
- 2026
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 i3-1215U / i3-1315U | 8.0 GB | 5.2 GB | 38 GB/s | 152 of 622 | $680 |
| Intel Core i3-1215U / i3-1315U · upgraded to the maker's maximum | 96.0 GB | 83.5 GB | 38 GB/s | 217 of 622 | — |
Specifications 96.0 GB configuration
| Maker | UGREEN |
|---|---|
| Type | NAS |
| Processor | Intel Core i3-1215U / i3-1315U NAS (96 GB) · upgraded to the maker's maximum |
| Memory (RAM) | 96.0 GB |
| Usable for AI models | 83.5 GB |
| Memory bandwidth | 38 GB/s |
| FP16 compute | 0.3 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 4x SATA + 2x M.2 NVMe |
| NAS system | UGOS Pro |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR5 SO-DIMM (up to 5200 MHz, non-ECC) · 2 slots · up to 96.0 GB per the maker · non-ECC |
| Notes | Intel Core i3-1315U (2P+4E, up to 4.5 GHz per Intel ARK and UGREEN China table; US page says 4.4 GHz). Up to 96 GB DDR5 but CPU-only inference; XDA measured about 3-5 tokens/s on 4B models (Qwen3, Gemma 3) with Ollama and Open WebUI. |
| Product page | ai.ugreen.com (opens in a new tab) |
Running AI on the UGREEN NASync DXP4800 Pro
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 83.5 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
| App | How it installs |
|---|---|
| Ollama | In a container (Docker) |
| Open WebUI | In a container (Docker) |
AI features from UGREEN
| Feature | What it does | Where the AI runs |
|---|---|---|
| AI Album (Photos app) | On-device photo recognition: faces, scenes/objects, text (OCR) and semantic photo search. Not a chat LLM. | On the NAS |
Best LLMs for the UGREEN NASync DXP4800 Pro 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 55.1 GB | 10.9 tok/s | Runs well |
| 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder Next (80B-A3B) | Q5_K_M | 64.0 GB | 10.4 tok/s | Runs well |
| 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q5_K_M | 65.2 GB | 10.4 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt 74B-A9B | Q5_K_M | 60.5 GB | 3.6 tok/s | Slow |
| 81Great quality (A) · 81 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Next 80B-A3B Instruct | Q5_K_M | 65.2 GB | 10.4 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q6_K | 40.1 GB | 10.5 tok/s | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 74.2 GB | 8.0 tok/s | Slowtight fit |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Super VL 120B-A12B | Q4_K_M | 83.3 GB | 3.2 tok/s | Slowtight fit |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q5_K_M | 33.0 GB | 10.4 tok/s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q5_K_M | 33.0 GB | 10.4 tok/s | Runs well |
Best Image models for the UGREEN NASync DXP4800 Pro 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | FP16 | 57.0 GB | 2.3 h | Very slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | FP16 | 57.3 GB | 58.1 min | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | Q8 GGUF | 61.9 GB | 1.6 h | Very slow |
| 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. | Cosmos3-Super Text2Image (64B) | FP8 | 69.1 GB | 83.7 min | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2512 | FP16 | 63.8 GB | 3.5 h | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 72.0 GB | 20.9 min | Very slowtight fit |
Best Video models for the UGREEN NASync DXP4800 Pro 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | Q8 GGUF | 68.2 GB | 46.3 h | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q8 GGUF | 49.8 GB | 4.1 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | FP16 | 58.0 GB | 62.0 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | FP16 | 58.0 GB | 62.0 h | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 1.5 (8.3B) | FP16 | 55.2 GB | 69.7 h | Very slow |
Best Decision models for the UGREEN NASync DXP4800 Pro 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 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. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 97 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 8.2 GB | 2.1 s | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 11.8 GB | 13.9 s | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q8_0 | 16.3 GB | 28.4 s | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 55.7 s | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 8.2 GB | 2.1 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 913 ms | Slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q8_0 | 11.8 GB | 13.9 s | Very slow |
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.