256GB max RAM · 8 bays · 2 x 10GbE
AINAS Score 42
No verified price
Traditional NASPromise
Why Traditional NAS: Intel Core i7-8700 with no NPU, no documented GPU path and a 128GB memory ceiling; Promise documents no Docker or container support, so the no Docker rule makes it traditional.
Updated
Can the Promise PegasusPro R16 run local AI?
The Promise PegasusPro R16 is a Traditional NAS built for file storage and backup rather than local AI. With Intel Core i7-8700 and a 128GB memory ceiling, it can run light services but not a useful local language model.
We list it so you can compare it with AI-capable systems at a similar price.
The PegasusPro R16 suits buyers who want a 16-bay rackmount storage appliance with fast networking and a long warranty, not a local AI box. It has an Intel Core i7-8700 with 6 cores, 64GB of DDR4 memory as sold, and a 550W power supply. Network ports are 4 x 10GbE and 2 x 1GbE, and it adds 2 Thunderbolt 3 ports for direct attachment. Promise gives it a 3 year warranty. It is managed with PROMISE Utility Pro on a PROMISE appliance OS. Its AINAS Score is 43, which reflects a traditional storage system rather than an AI one.
The main thing that rules it out is that nothing on it can run model software. Promise documents no Docker, container or LLM support, and we class it as traditional for that reason. There is no NPU and no documented GPU path, so memory alone does not make it an AI machine. Anyone who wants local LLMs, private RAG or AI search should look for a system with confirmed container support, a documented GPU or NPU route, and enough memory headroom. Its 2 PCIe slots have no stated type either, so even a card route cannot be planned.
No verified price
We have not verified a listing for the Promise PegasusPro R16 at a retailer we track. The specifications below stand on their own; a price appears here as soon as a listing is confirmed.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon.co.uk or Amazon.com, as applicable, at the time of purchase will apply to the purchase of this product.
Each capability shows how it was confirmed: Verified by AINAS, Vendor confirmed, Community confirmed or Unverified.
| Capability | Supported | Evidence | Note |
|---|---|---|---|
| Local LLM | No | Unverified | No Docker, container or LLM support in the datasheet. |
| Ollama | No | Unverified | No evidence found. |
| Open WebUI | No | Unverified | No evidence found. |
| RAG | No | Unverified | No evidence found. |
| AI search | No | Unverified | No AI search feature documented. |
| GPU expansion | No | Unverified | PCIe slots listed but no GPU use documented. |
| Hardware acceleration | No | Unverified | No acceleration documented. |
| AI photos | No | Unverified | No feature documented. |
| AI video | No | Unverified | Application list covers editing software only; no AI video feature. |
| Surveillance AI | No | Unverified | No feature documented. |
Calculated from the PegasusPro R16's memory and each model's published size at each quantization. Rows marked Estimated are calculations, not benchmarks. Check any model.
| Model | Best quantization | Runs? | Memory needed | Expected performance | Verification |
|---|---|---|---|---|---|
| Llama 3.2 3BLlama, 3.21B | Q8 | Yes | 13GB | Not measured | Estimated |
| Llama 3.1 8BLlama, 8.03B | Q8 | Yes | 19GB | Not measured | Estimated |
| Qwen3 8BQwen, 8.19B | Q8 | Yes | 19GB | Not measured | Estimated |
| Gemma 3 12BGemma, 11.8B | Q8 | Yes | 24GB | Not measured | Estimated |
| Qwen3 14BQwen, 14.8B | Q8 | Yes | 28GB | Not measured | Estimated |
| Phi-4 14BPhi, 14.7B | Q8 | Yes | 28GB | Not measured | Estimated |
| Mistral Small 3 24BMistral, 23.6B | Q8 | Yes | 38GB | Not measured | Estimated |
| Gemma 3 27BGemma, 27B | Q8 | Yes | 44GB | Not measured | Estimated |
| Qwen3 30B A3BQwen, 30.5B | Q8 | Yes | 47GB | Not measured | Estimated |
| Qwen3 32BQwen, 32.8B | Q8 | Yes | 50GB | Not measured | Estimated |
| DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8B | Q8 | Yes | 50GB | Not measured | Estimated |
| Llama 3.3 70BLlama, 70.6B | Q8 | Yes | 98GB | Not measured | Estimated |
| Llama 4 Scout 17Bx16ELlama, 109B | Q4 | Yes | 89GB | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | Q8 | Yes | 101GB | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | Q5 | Yes | 112GB | Not measured | Estimated |
One verdict per workload, from the PegasusPro R16's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The PegasusPro R16 is a poor choice for running local LLMs. The local LLM and Ollama rows both say no (Unverified), the datasheet shows no Docker, container or LLM support, and there is no NPU or GPU path.
The PegasusPro R16 is a poor fit for private RAG. The RAG, Open WebUI and Ollama rows all say no and are Unverified, with no evidence found, and it has no documented container support to host them.
AI search is a poor fit on the PegasusPro R16. The datasheet documents no AI search feature, so the capability is recorded as no (Unverified), and the system has no NPU to offload any such work.
The PegasusPro R16 is poor for AI photo tagging. The AI photos row says no (Unverified) because no feature is documented, and the system has no NPU or GPU path that could support one.
Surveillance is a poor fit for the PegasusPro R16. The surveillance row says no (Unverified) with no feature documented, so there is no confirmed camera recording or AI detection support.
We cannot confirm how well the PegasusPro R16 suits a home lab. Docker and virtual machine support are not documented, so those uses are unconfirmed, though it does offer 16 bays and 4 x 10GbE.
The PegasusPro R16 is an OK business option. It offers 16 bays in a rackmount case, 64GB of memory expandable to 128GB, 10GbE networking and a 3 year warranty, with no AI features involved.
Creative AI is a poor fit for the PegasusPro R16. GPU expansion and hardware acceleration both say no (Unverified), the PCIe slots have no documented GPU use, and local LLM support is also absent.
The PegasusPro R16 ships with 64GB of DDR4 and supports up to 128GB. Upgrading to the maximum lifts the model ceiling from 32B class models comfortably, and 70B class models at 4-bit with little headroom to 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit (both Estimated).
As a rule of thumb, a 4-bit model needs about 0.6GB per billion parameters plus room for context. After leaving around 8GB for the NAS operating system, 128GB leaves space for a model of roughly 200B parameters at most (Estimated).
No. The PegasusPro R16 has no PCIe slot or OCuLink port for a graphics card, and eGPU use over USB4 or Thunderbolt is not a supported NAS setup. Inference runs on the CPU, so keep to small models.
Not well. A useful private RAG setup needs more memory or compute than the PegasusPro R16 offers.
Networking is 4 x 10GbE + 2 x 1GbE. That is ample for indexing large libraries and for several people querying at once.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| Standard, 64GB | 64GB | None |
The closest Promise model by bay count and AINAS Score. Only the specifications that differ are listed.
The PegasusPro R16 scores best for Home Lab (61/100) and Business (59/100). It suits home lab owners who want one box for storage, containers, media and a few AI services.
It is a weaker fit for buyers who expect to add a graphics card later.
Other Traditional NAS systems closest in overall score.
Workloads it suits
No. Memory alone would hold the model, with an Estimated 73GB needed at Q4 against a 128GB ceiling. But the system has no container or LLM support, so nothing on it can run the model. We treat it as a storage appliance, not an AI system.
It ships with 64GB of DDR4 and takes up to 128GB. The memory is expandable, so you can add to the 64GB that comes in the standard configuration. Promise does not state ECC support, so do not assume it.
No, not as far as we can confirm. Promise documents no Docker or container support, and the local LLM and Ollama rows are both marked no and Unverified. That is why we class it as traditional rather than as an AI system.
No, not as documented. It lists 2 PCIe slots but does not state their type, and no GPU use is described. The GPU expansion row says no and is Unverified. It also has no OCuLink port.
Yes. It has 2 Thunderbolt 3 ports and no USB4 ports. Promise describes it as a hybrid NAS and Thunderbolt DAS family. It also has 4 x 10GbE and 2 x 1GbE network ports for standard network use.
16. The PegasusPro R16 is a 16-bay rackmount appliance, and it has no M.2 or NVMe slots, so every drive sits in those bays. Storage reaches clients over 4 x 10GbE and 2 x 1GbE, or directly over the 2 Thunderbolt 3 ports when it works as attached storage. The Standard configuration has 64GB of DDR4, expandable to 128GB, the power supply is 550W and the warranty is 3 years.
No. Ollama support is not yet verified. See the capability table above for the source.
No. Open WebUI support is not yet verified. See the capability table above for the source.
No. AI photos support is not yet verified. See the capability table above for the source.
No. Surveillance AI support is not yet verified. See the capability table above for the source.
No. Hardware acceleration support is not yet verified. See the capability table above for the source.
It has 4 x 10GbE + 2 x 1GbE built in, and the 2 PCIe slots listed; type not stated can take a faster network card. The fastest port is 4 x 10GbE.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.