Products · Synology · NAS
Synology HD6500
- Processor
- Intel Xeon Silver (4100 to 4300 series)
- Memory (RAM)
- 64 or 512 GB
- Released
- 2022
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 Xeon Silver (4100 to 4300 series) | 64.0 GB | 54.4 GB | 115 GB/s | 358 of 619 | — |
| Intel Xeon Silver (4100 to 4300 series) · upgraded to the maker's maximum | 512 GB | 471 GB | 115 GB/s | 366 of 619 | — |
Specifications 64.0 GB configuration
| Maker | Synology |
|---|---|
| Type | NAS |
| Processor | Intel Xeon Silver (4100 to 4300 series) NAS (64 GB) |
| Memory (RAM) | 64.0 GB |
| Usable for AI models | 54.4 GB |
| Memory bandwidth | 115 GB/s |
| FP16 compute | 1.0 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 60x 3.5" SAS HDD or 2.5" SATA SSD |
| NAS system | DSM 7.x |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR4 ECC RDIMM · 16 slots · up to 512 GB per the maker · ECC |
| Graphics card options | PCIe: 2 x Gen3 x16 slot (x16 link) + 2 x Gen3 x8 slot (x8 link). |
| Notes | 2 x Intel Xeon Silver 4210R. x86-64 CPU (2 x Intel Xeon Silver 4210R, 2 x 10C/20T), RAM upgradable to 512 GB, and Container Manager (Docker) plus Virtual Machine Manager are supported, so Ollama/llama.cpp run on the NAS. CPU-only: no GPU option, so expect small-to-mid quantized models at low tokens per second. |
| Product page | www.synology.com (opens in a new tab) |
Running AI on the Synology HD6500
Yes, it runs AI models on the NAS itself. Models run on its CPU cores, and this configuration leaves about 54.4 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 + 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 |
| AI Console de-identification | Masks names and other sensitive entities before text is sent to a remote AI provider, using small local language models run through Container Manager. | On the NAS |
Best LLMs for the Synology HD6500 64.0 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 88/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 52.8 GB | 18.6 tok/s | Runs welltight fit |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q4_K_M | 29.5 GB | 25.1 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q4_K_M | 27.0 GB | 21.2 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q4_K_M | 27.0 GB | 21.2 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 26.6 GB | 21.2 tok/s | Runs well |
| 81Great quality (A) · 81 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. | Qwen3 Coder Next (80B-A3B) | Q4_K_M | 53.8 GB | 21.2 tok/s | Runs welltight fit |
| 87Excellent quality (A+) · 87 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. | Nex N2 Mini (35B-A3B) | Q4_K_M | 26.5 GB | 21.2 tok/s | Runs well |
| 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. | Sage-A1.5 35B-A3B | Q4_K_M | 27.0 GB | 21.2 tok/s | Runs well |
| 86Excellent quality (A+) · 86 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. | KAT-Coder V2.5 Dev (35B-A3B) | Q4_K_M | 26.3 GB | 21.2 tok/s | Runs well |
| 85Excellent quality (A+) · 85 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. | Ornith 1.5 35B-A3B | Q4_K_M | 27.0 GB | 21.2 tok/s | Runs well |
Best Image models for the Synology HD6500 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 3.5 min | Very slow |
| 84Great quality (A) · 84 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. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 89 s | Slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | Q8 GGUF | 41.6 GB | 56.7 min | Very slow |
| 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. | Qwen-Image 2512 | Q8 GGUF | 36.5 GB | 85.1 min | Very slow |
| 88Excellent quality (A+) · 88 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. | ERNIE-Image | FP16 | 34.0 GB | 18.1 min | Very slow |
| 93Excellent quality (A+) · 93 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. | Fibo 2.0 Dev | FP16 | 27.7 GB | 18.5 min | Very slow |
Best Video models for the Synology HD6500 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 87Excellent quality (A+) · 87 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. | LTX-2.5 (22B, video + audio) | Q8 GGUF | 49.8 GB | 86.0 min | Very slowtight fit |
| 85Excellent quality (A+) · 85 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-2.3 | Q8 GGUF | 45.6 GB | 6.3 h | Very slow |
| 85Excellent quality (A+) · 85 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. | Bernini-R A14B (video generation + editing) | FP16 | 46.0 GB | 9.9 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | Q8 GGUF | 39.3 GB | 25.2 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | Q8 GGUF | 39.3 GB | 25.2 h | Very slow |
Best Decision models for the Synology HD6500 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | F16 | 3.8 GB | 50 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 117 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 5.8 GB | 899 ms | Slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 394 ms | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 5.8 GB | 899 ms | Slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 9.5 GB | 6.0 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 | 13.9 GB | 12.2 s | Very slow |
| 80Great quality (A) · 80 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. | FRIDA-Decisions | Q8_0 | 1.7 GB | 656 ms | Slow |
Other products with the Intel Xeon Silver (4100 to 4300 series) NAS (64 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.