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 Atom C5125 | 8.0 GB | 5.2 GB | 24 GB/s | 108 of 622 | — |
| Intel Atom C5125 · upgraded to the maker's maximum | 128 GB | 113 GB | 24 GB/s | 148 of 622 | — |
Specifications 128 GB configuration
| Maker | QNAP |
|---|---|
| Type | NAS |
| Processor | Intel Atom C5125 NAS (128 GB) · upgraded to the maker's maximum |
| Memory (RAM) | 128 GB |
| Usable for AI models | 113 GB |
| Memory bandwidth | 24 GB/s |
| FP16 compute | 0.2 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 12 x 3.5-inch + 4 x 2.5-inch SATA 6Gb/s, 3Gb/s + M.2: 2 x M.2 2280 PCIe Gen 3 x2 slots |
| NAS system | QTS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | UDIMM DDR4 · 4 slots · up to 128 GB per the maker · ECC |
| Graphics card options | PCIe: 3 Slot 1: PCIe Gen 3 x4 Slot 2: PCIe Gen 3 x4 Slot 3: PCIe Gen 3 x4. |
| Notes | Intel Atom C5125 8-core processor, 2.8GHz. x86-64 Atom C5125 CPU, up to 128 GB RAM, Container Station (Docker) and Virtualization Station. Has PCIe slot(s), but the maker spec sheet does not list GPU pass-through for this model; treat as CPU-only unless verified. |
| Product page | www.qnap.com (opens in a new tab) |
Running AI on the QNAP TS-1655
Yes, it runs AI models on the NAS itself. Models run on its CPU cores, and this configuration leaves about 113 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) |
| Ollama / Open WebUI or any other LLM server image | In a container (Docker) |
| Any Linux VM running an LLM runtime | In a virtual machine |
AI features from QNAP
| Feature | What it does | Where the AI runs |
|---|---|---|
| Qsirch RAG Search (cloud LLM mode) | Natural-language search and Q&A over NAS files; retrieval runs on the NAS but the LLM is a cloud API (Gemini, OpenAI, Azure OpenAI or OpenAI-compatible). | Cloud service or another computer |
Best LLMs for the QNAP TS-1655 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q6_K | 73.8 GB | 4.0 tok/s | Slow |
| 92Excellent quality (A+) · 92 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. | Nemotron 3.5 Super VL 120B-A12B | Q6_K | 112 GB | 1.2 tok/s | Very slowtight fit |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 76.5 GB | 4.1 tok/s | Slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Super 120B-A12B | Q6_K | 111 GB | 1.2 tok/s | Very slowtight fit |
| 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Flash Next (125B-A6B) | Q3_K_M | 98.0 GB | 4.3 tok/s | Slowtight fit |
| 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Flash (127B-A5B) | Q4_K_M | 87.8 GB | 3.9 tok/s | Slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.6V | Q5_K_M | 87.6 GB | 1.4 tok/s | Very slow |
| 95Excellent quality (A+) · 95 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. | Nanbeige4.3 33B | Q8_0 | 46.5 GB | 0.3 tok/s | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 4 (119B-A6B) | Q4_K_M | 82.6 GB | 3.3 tok/s | Slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Solar Open 100B | Q6_K | 95.4 GB | 1.2 tok/s | Very slow |
Best Image models for the QNAP TS-1655 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 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. | MiniMax H3 Image | FP8 | 72.0 GB | 30.7 min | Very slow |
| 90Excellent quality (A+) · 90 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. | Cosmos3-Super Text2Image (64B) | FP8 | 69.1 GB | 2.0 h | Very slow |
| 88Excellent quality (A+) · 88 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. | HunyuanImage 3.0 (80B-A13B) | FP8 | 86.9 GB | 3.1 h | Very slow |
| 91Excellent quality (A+) · 91 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. | FLUX.2 [dev] | Q8 GGUF | 61.9 GB | 2.4 h | Very slow |
| 93Excellent quality (A+) · 93 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. | Qwen-Image 2.1 | FP16 | 57.0 GB | 3.4 h | Very slow |
| 90Excellent quality (A+) · 90 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. | Qwen-Image 2512 | FP16 | 63.8 GB | 5.1 h | Very slow |
Best Video models for the QNAP TS-1655 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 5.2 h | Very slow |
| 88Excellent quality (A+) · 88 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. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 167.1 h | Very slow |
| 89Excellent quality (A+) · 89 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. | MiniMax H3 (33B, video + audio) | Q8 GGUF | 68.2 GB | 68.0 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. | LTX-2.3 | FP16 | 75.4 GB | 22.7 h | Very slow |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2 (19B, video + audio) | FP16 | 75.4 GB | 22.7 h | Very slow |
Best Decision models for the QNAP TS-1655 128 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 83/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 190 ms | Runs well |
| 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 | 14.2 GB | 27.8 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 | 18.6 GB | 56.7 s | Very slow |
| 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 | 10.5 GB | 4.2 s | Very slow |
| 90Excellent quality (A+) · 90 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. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 111.3 s | Very 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 | 14.2 GB | 27.8 s | Very slow |
| 84Great quality (A) · 84 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. | Jina Reranker v3 | Q8_0 | 10.5 GB | 4.2 s | Very slow |
| 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. | Shieldstral 1.0 3B | Q8_0 | 13.9 GB | 26.7 s | Very slow |
Other products with the Intel Atom C5125 NAS (128 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.