Products · QNAP · NAS
QNAP TS-h987XU-RP
- Processor
- Intel Xeon E-2300
- Memory (RAM)
- 16 or 128 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 E-2300 | 16.0 GB | 12.0 GB | 51 GB/s | 231 of 622 | — |
| Intel Xeon E-2300 · upgraded to the maker's maximum | 128 GB | 113 GB | 51 GB/s | 276 of 622 | — |
Specifications 16.0 GB configuration
| Maker | QNAP |
|---|---|
| Type | NAS |
| Processor | Intel Xeon E-2300 NAS (16 GB) |
| Memory (RAM) | 16.0 GB |
| Usable for AI models | 12.0 GB |
| Memory bandwidth | 51 GB/s |
| FP16 compute | 0.5 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 9 (4 x 3.5-inch SATA + 5 x 2.5-inch U.2 PCIe / SATA) |
| NAS system | QuTS hero |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR4 UDIMM · 4 slots · up to 128 GB per the maker · ECC |
| Graphics card options | PCIe: 1 x Gen4 x8. |
| Notes | Intel Xeon E-2334 4C 8T 3.4GHz, up to 4.8GHz. x86-64 with up to 128 GB RAM and Container Station; Ollama runs CPU-only per QNAP's tutorial (>=8 GB for 3B, >=16 GB for 7B models). QNAP does not list a GPU-capable slot for this model, so its own on-prem Qsirch LLM (GPU required) is not available. No token speeds published. |
| Product page | www.qnap.com (opens in a new tab) |
Running AI on the QNAP TS-h987XU-RP
Yes, it runs AI models on the NAS itself. Models run on its CPU cores, and this configuration leaves about 12.0 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 QNAP
| Feature | What it does | Where the AI runs |
|---|---|---|
| QuMagie + QNAP AI Core | Photo management with on-device face, object and scene recognition (QNAP AI Core image-recognition engine). | On the NAS |
| Qsirch AI Semantic Search | Natural-language/semantic file and image search computed locally; QNAP requires a 64-bit x86 NAS with at least 8 GB RAM. | On the NAS |
| Qsirch RAG Search (cloud LLM mode) | Chat with NAS files using a cloud LLM (Gemini, OpenAI, Azure OpenAI or OpenAI-compatible API); the model runs remotely. | Cloud service or another computer |
| QuAgent (beta) + AI Service Center (beta) | Conversational NAS assistant on QTS 6.1 / QuTS hero h6.1; uses either a cloud model or an on-premises model (compatible GPU recommended). QNAP lists x86 NAS "x74 series and above", TVS-AI and QAI series as supported. | Cloud service or another computer |
Best LLMs for the QNAP TS-h987XU-RP 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 12B | Q4_K_M | 9.5 GB | 4.0 tok/s | Slow |
| 79Great quality (A) · 79 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. | K2 Horizon 7B | Q6_K | 10.1 GB | 3.7 tok/s | Slow |
| 66Good quality (B) · 66 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. | Mellum2.1 Thinking (12B-A2.5B) | Q4_K_M | 9.1 GB | 18.0 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q3_K_M | 11.6 GB | 36.7 tok/s | Runs welltight fit |
| 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Distill Qwen 9B | Q6_K | 9.5 GB | 3.5 tok/s | Slow |
| 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova Loop 9B Preview | Q6_K | 10.0 GB | 3.4 tok/s | Slow |
| 76Great quality (A) · 76 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. | Ornith 1.5 9B | Q6_K | 9.7 GB | 3.5 tok/s | Slow |
| 75Great quality (A) · 75 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. | Qwen3.5 9B | Q6_K | 9.7 GB | 3.5 tok/s | Slow |
| 74Great quality (A) · 74 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 9B | Q6_K | 9.7 GB | 3.5 tok/s | Slow |
| 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | TMax 9B | Q6_K | 9.2 GB | 3.7 tok/s | Slow |
Best Image models for the QNAP TS-h987XU-RP 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q4 GGUF | 10.2 GB | 10.2 min | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP8 | 10.2 GB | 81 s | Slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | Q4 GGUF | 10.1 GB | 4.5 min | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | Q4 GGUF | 11.3 GB | 5.7 min | Very slowtight fit |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image | Q4 GGUF | 10.1 GB | 30.5 min | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | Q4 GGUF | 8.0 GB | 3.4 min | Very slowencoder unloaded after use |
Best Video models for the QNAP TS-h987XU-RP 16.0 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 64/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 10.8 GB | 33.7 min | Slowtight fit |
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP8 | 10.7 GB | 21.0 h | Very slowtight fit · CPU offload |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 7.8 GB | 15.5 h | Very slowCPU offload |
| 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 1.3B | FP16 | 8.4 GB | 6.3 h | Very slowencoder unloaded after use |
| 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 VACE 1.3B | FP16 | 10.1 GB | 6.8 h | Very slowencoder unloaded after use |
Best Decision models for the QNAP TS-h987XU-RP 16.0 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 | 69 ms | Runs great |
| 86Excellent quality (A+) · 86 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 v3.5 | Q8_0 | 2.4 GB | 1.3 s | Slow |
| 80Great quality (A) · 80 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 555 ms | Slow |
| 68Good quality (B) · 68 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. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 164 ms | Runs well |
| 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 | 6.1 GB | 8.5 s | Very slow |
| 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 | 2.4 GB | 1.3 s | Slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q6_K | 8.6 GB | 17.2 s | Very slow |
| 88Excellent quality (A+) · 88 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. | zerank-2 | Q8_0 | 6.1 GB | 8.5 s | Very slow |
Other products with the Intel Xeon E-2300 NAS (16 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.