Products · QNAP · NAS
QNAP QAI-h1290FX
- Processor
- AMD EPYC 7002 / 7003 series
- Memory (RAM)
- 128 or 512 GB
- 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 |
|---|---|---|---|---|---|
| AMD EPYC 7002 / 7003 series | 128 GB | 113 GB | 205 GB/s | 441 of 619 | — |
| AMD EPYC 7002 / 7003 series · upgraded to 512 GB (the maker lists up to 1 TB) | 512 GB | 471 GB | 205 GB/s | 459 of 619 | — |
Specifications 128 GB configuration
| Maker | QNAP |
|---|---|
| Type | NAS |
| Processor | AMD EPYC 7002 / 7003 series NAS (128 GB) |
| Memory (RAM) | 128 GB |
| Usable for AI models | 113 GB |
| Memory bandwidth | 205 GB/s |
| FP16 compute | 1.0 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 12 x 2.5-inch U.2 PCIe NVMe / SATA 6Gbps |
| NAS system | QuTS hero |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR4 RDIMM · 8 slots · up to 1,024 GB per the maker · ECC |
| Graphics card options | PCIe: 4 ; Slot 1: PCIe Gen 4 x16 ; Slot 2: PCIe Gen 4 x16 ; Slot 3: PCIe Gen 4 x8 ; Slot 4: PCIe Gen 4 x16. Maker-supported graphics cards: NVIDIA RTX PRO 6000 Blackwell Max-Q (96 GB), NVIDIA RTX PRO 4500 Blackwell (32 GB) as factory options; Intel Arc Pro B70 support added in QuTS hero h6.1 (BIOS update from QNAP support required). |
| Notes | AMD EPYC 7302P 16-core/32-thread processor, up to 3.3 GHz. Purpose-built Edge AI storage server: EPYC 7302P, 128 GB RAM (max 1 TB), sold with an NVIDIA RTX PRO Blackwell GPU and Ollama/Open WebUI/AnythingLLM container templates. |
| Product page | www.qnap.com (opens in a new tab) |
Running AI on the QNAP QAI-h1290FX
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, AnythingLLM, Stable Diffusion | From the NAS app store |
| 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 |
| Ollama | In a container (Docker) |
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 |
| LLM Core + Qsirch on-premises RAG | Runs open LLMs locally on an NVIDIA GPU in the NAS (GPU set to Container Station mode) for Qsirch RAG; QNAP lists DeepSeek R1 7B-32B, Gemma3 1B-27B, gpt-oss 20B, Mistral 7B, Phi-4 14B (Q4_K_M). | On the NAS |
| Preloaded AI container templates (Ollama, Open WebUI, AnythingLLM, Whisper) | QNAP-provided Container Station templates for local LLM chat, RAG and speech-to-text on the built-in NVIDIA GPU; Stable Diffusion, ComfyUI, n8n and vLLM listed as planned. | On the NAS |
| 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 on-premises RAG / LLM Core | Runs open models (DeepSeek R1, Gemma 3, gpt-oss 20B, Mistral 7B, Phi-4) locally for RAG search. Requires an NVIDIA GPU assigned to Container Station; QNAP states CPU-only is not supported. Needs QuTS hero h5.2.1+ and Qsirch 6.0.0+. | On the NAS |
Best LLMs for the QNAP QAI-h1290FX 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 76.5 GB | 26.7 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 89/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 57.4 GB | 35.5 tok/s | Runs great |
| 81Great quality (A) · 81 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. | Qwen3-Next 80B-A3B Thinking | Q4_K_M | 59.4 GB | 40.2 tok/s | Runs great |
| 81Great quality (A) · 81 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. | Qwen3 Coder Next (80B-A3B) | Q4_K_M | 58.4 GB | 40.2 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt 74B-A9B | Q6_K | 71.1 GB | 10.4 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 88/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 122B-A10B | Q4_K_M | 86.1 GB | 13.3 tok/s | Runs well |
| 79Great quality (A) · 79 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. | Qwen3 Next 80B-A3B Instruct | Q4_K_M | 59.4 GB | 40.2 tok/s | Runs great |
| 89Excellent quality (A+) · 89 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. | Nemotron 3.5 Super VL 120B-A12B | Q4_K_M | 85.6 GB | 11.2 tok/s | Runs well |
| 87Excellent quality (A+) · 87 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 122B-A10B | Q4_K_M | 86.1 GB | 13.3 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Flash Next (125B-A6B) | Q3_K_M | 98.0 GB | 27.4 tok/s | Runs welltight fit |
Best Image models for the QNAP QAI-h1290FX 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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 | 24.7 min | 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 | 37.0 min | 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 | 28.4 min | Very slow |
| 92Excellent quality (A+) · 92 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. | Ideogram 4 | FP16 | 57.3 GB | 17.1 min | Very slow |
| 93Excellent quality (A+) · 93 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. | Qwen-Image 2.1 | FP16 | 57.0 GB | 41.1 min | Very slow |
| 90Excellent quality (A+) · 90 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. | Qwen-Image 2512 | FP16 | 63.8 GB | 61.6 min | Very slow |
Best Video models for the QNAP QAI-h1290FX 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 82/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 62.3 min | Very slow |
| 86Excellent quality (A+) · 86 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. | LTX-2.3 | FP16 | 75.4 GB | 4.6 h | 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. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 33.6 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 | 13.7 h | Very slow |
| 82Great quality (A) · 82 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. | LTX-2 (19B, video + audio) | FP16 | 75.4 GB | 4.6 h | Very slow |
Best Decision models for the QNAP QAI-h1290FX 128 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 | 44 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 103 ms | Runs great |
| 80Great quality (A) · 80 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 345 ms | Runs well |
| 86Excellent quality (A+) · 86 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. | Jina Reranker v3.5 | Q8_0 | 10.5 GB | 780 ms | Slow |
| 84Great quality (A) · 84 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 | Q8_0 | 10.5 GB | 780 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 | 14.2 GB | 5.2 s | Very slow |
| 66Good quality (B) · 66 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. | GLiClass Base v3 | Q8_0 | 0.8 GB | 136 ms | Runs well |
| 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. | FRIDA-Decisions | Q8_0 | 1.7 GB | 574 ms | Slow |
Other products with the AMD EPYC 7002 / 7003 series 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.