Products · Synology · NAS
Synology DS225+
- Processor
- Intel Celeron J4125 / J4105
- Memory (RAM)
- 6 GB
- Released
- 2025
Specifications
| Maker | Synology |
|---|---|
| Type | NAS |
| Processor | Intel Celeron J4125 / J4105 NAS (6 GB) · upgraded to the maker's maximum |
| Memory (RAM) | 6.0 GB |
| Usable for AI models | 3.5 GB |
| Memory bandwidth | 19 GB/s |
| FP16 compute | 0.0 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 2x 3.5" SATA HDD or 2.5" SATA SSD |
| NAS system | DSM 7.x |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR4 non-ECC (2 GB onboard + 1 slot) · 1 slot · up to 6.0 GB per the maker · non-ECC |
| Notes | Intel Celeron J4125. x86-64 with Container Manager, but RAM tops out at 6 GB officially and the Intel Celeron J4125 (4C/4T) is a low-power CPU (Celeron J-series lack AVX), so only 1-4B-parameter quantized models are realistic, slowly. |
| Product page | www.synology.com (opens in a new tab) |
Running AI on the Synology DS225+
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 3.5 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.
Apps you can install to run models
| App | How it installs |
|---|---|
| Ollama + Open WebUI | In a container (Docker) |
| Any Linux guest running llama.cpp / Ollama | In a virtual machine |
AI features from Synology
| Feature | What it does | Where the AI runs |
|---|---|---|
| Synology AI Console (cloud providers) | Admin console that connects Synology Office, MailPlus, Chat, Drive etc. to Amazon Bedrock, Azure OpenAI, Baidu AI Cloud, Google AI Studio/Vertex AI, OpenAI or any OpenAI-compatible endpoint. | Cloud service or another computer |
Best LLMs for the Synology DS225+
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q4_K_M | 2.8 GB | 3.2 tok/s | Slow |
| 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | LFM3 1.7B | Q6_K | 2.4 GB | 3.3 tok/s | Slow |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | Q3_K_M | 3.5 GB | 4.6 tok/s | Slowtight fit |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q4_K_M | 3.4 GB | 13.0 tok/s | Runs welltight fit |
| 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | LFM3-VL 2B | Q5_K_M | 2.3 GB | 3.5 tok/s | Slow |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | Q3_K_M | 3.4 GB | 2.3 tok/s | Very slowtight fit |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | Q2_K | 2.9 GB | 3.4 tok/s | Slow |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 4B | Q3_K_M | 3.4 GB | 2.3 tok/s | Very slowtight fit |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q2_K | 2.8 GB | 3.3 tok/s | Slow |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR (3B-A0.6B) | Q4_K_M | 3.4 GB | 13.0 tok/s | Runs welltight fit |
Best Image models for the Synology DS225+
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | Q4 GGUF | 2.9 GB | 14.3 min | Very slowCPU offload |
| 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 2.8 GB | 11.0 min | Very slow |
| 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper 8 | FP16 | 2.8 GB | 11.0 min | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | MOSS-Image SFT | Q4 GGUF | 3.3 GB | 3.3 h | Very slowtight fit · CPU offload |
| 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | SD Turbo | FP16 | 3.3 GB | 44 s | Slowtight fit |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 1.5 | FP16 | 2.8 GB | 11.0 min | Very slow |
Best Video models for the Synology DS225+
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 2.6 GB | 4.0 h | Very slowCPU offload |
Best Decision models for the Synology DS225+
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 1.7 GB | 30.9 s | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 1.7 GB | 30.9 s | Very slow |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q8_0 | 2.6 GB | 79.2 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 13.6 s | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 1.4 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | Q8_0 | 1.7 GB | 22.8 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | Q8_0 | 1.7 GB | 30.9 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | zerank-1 small | Q8_0 | 2.9 GB | 88.5 s | Very slow |
Other products with the Intel Celeron J4125 / J4105 NAS (6 GB)
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.