128GB max RAM · 16 bays · 4 x 10GbE
AINAS Score 43
No verified price
Traditional NASOWCDiscontinued
Why Traditional NAS: Intel Xeon Scalable (model unpublished) with no documented GPU path and a 256GB memory ceiling, but OWC documents no Docker or container support, so the no Docker rule makes it traditional.
Updated
Can the OWC Jellyfish Mobile run local AI?
The OWC Jellyfish Mobile is a Traditional NAS built for file storage and backup rather than local AI. With Intel Xeon Scalable (model not published) and a 256GB 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 Jellyfish Mobile suits video teams who want a portable shared-storage appliance with 8 bays, 128GB of memory (256GB maximum) and 2 x 10GbE ports. It is a closed storage system managed through Jellyfish Manager, which is the appliance OS (the underlying name is not published). The CPU is an Intel Xeon Scalable, though the exact model and core count are not published. It was released in 2022 and carries an AINAS Score of 42. It is not aimed at AI work, and the AINAS class is traditional. Treat it as shared storage for editors, with the 10GbE links carrying the traffic. Configurations seen are 48TB and 96TB, both with 128GB of memory.
The main thing that rules it out is its status. OWC has discontinued the Jellyfish Mobile and names the Jellyfish Studio as its replacement. The warranty length is not published, and neither are the CPU model, memory type or ECC status, so support for an older unit is hard to plan around. Anyone who needs a supported system should look for a current model with a published warranty and full specifications. Buyers who want local AI should look for documented container support, a GPU path or an NPU. The Jellyfish Mobile documents none of these. Its 128GB of memory would hold models, but nothing on the system can run them.
No verified price
We have not verified a listing for the OWC Jellyfish Mobile 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 documented by OWC; closed video storage appliance. |
| 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 | No GPU path documented. |
| Hardware acceleration | No | Unverified | No GPU or accelerator documented. |
| AI photos | No | Unverified | No feature documented. |
| AI video | No | Unverified | No AI video feature documented. |
| Surveillance AI | No | Unverified | No feature documented. |
Calculated from the Jellyfish Mobile'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 | Q8 | Yes | 149GB | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | Q8 | Yes | 101GB | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | Q8 | Yes | 164GB | Not measured | Estimated |
One verdict per workload, from the Jellyfish Mobile's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The Jellyfish Mobile is a poor choice for a local LLM. Local LLM support is marked no and Unverified, and the notes say no Docker, container or LLM support is documented for this closed video storage appliance.
Private RAG is a poor fit on the Jellyfish Mobile. The RAG, Open WebUI and Ollama rows are all marked no and Unverified, with no evidence found, so there is nothing to build a document pipeline on.
AI search is a poor fit here. The AI search row is marked no and Unverified, and the notes say no AI search feature is documented, so the appliance offers only storage.
AI photo features are a poor fit on the Jellyfish Mobile. The AI photos row is marked no and Unverified, with the notes saying no feature is documented, and no NPU is listed.
Surveillance is a poor fit for the Jellyfish Mobile. The surveillance row is marked no and Unverified, with no feature documented, so it is not a camera recording or analysis system.
We cannot confirm how the Jellyfish Mobile suits a home lab. Docker and virtual machine support are both unpublished, and the appliance OS is managed through Jellyfish Manager, so tinkering room is unclear.
The Jellyfish Mobile is OK for business use as shared storage. It has 8 bays, 2 x 10GbE and 128GB of memory, but it is discontinued and its warranty is not published.
Creative AI is a poor fit. GPU expansion is marked no and Unverified with no GPU path documented, hardware acceleration is also no, and local LLM support is not documented.
The Jellyfish Mobile ships with 128GB of memory and supports up to 256GB. Upgrading to the maximum lifts the model ceiling from 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit 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, 256GB leaves space for a model of roughly 413B parameters at most (Estimated).
No. The Jellyfish Mobile has no PCIe slot or OCuLink port for a graphics card. Inference runs on the CPU, so keep to small models.
Not well. A useful private RAG setup needs more memory or compute than the Jellyfish Mobile offers.
Networking is 2 x 10GbE. That is ample for indexing large libraries and for several people querying at once.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 48TB, 128GB | 128GB | None | |
| 96TB, 128GB | 128GB | None |
The closest OWC model by bay count and AINAS Score. Only the specifications that differ are listed.
The Jellyfish Mobile scores best for Home Lab (57/100) and Business (56/100). 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 and for buyers who want a model with a long support life ahead.
Other Traditional NAS systems closest in overall score.
No. The system cannot run model software. No Docker or container support is documented and local LLM support is marked no and Unverified. Its memory is estimated to hold Qwen3 235B A22B at Q4, but that is a calculation only, and nothing on the system could run the model. It is a closed video storage appliance, not an AI platform.
It ships with 128GB and the maximum is 256GB. The memory type is not published, and OWC does not say whether it is upgradeable or has ECC. Both configurations seen, 48TB and 96TB, carry 128GB. The memory serves the storage appliance, not AI workloads.
8. The Jellyfish Mobile is an 8-bay portable shared-storage appliance, seen in 48TB and 96TB configurations, both with 128GB of memory. No M.2 slots are listed, so there is no separate flash tier for caching. Editors reach the drives over the 2 x 10GbE ports, and OWC says up to 14 editors can connect over 10G or 1G. Management runs through Jellyfish Manager rather than a general-purpose operating system.
No. OWC documents no GPU path, no PCIe slot is listed and there is no OCuLink, Thunderbolt or USB4 port, so there is nowhere to attach a card. GPU expansion and hardware acceleration are both marked no and Unverified, and there is no NPU. Even with a card, no Docker or container support is documented, so no model software could use it. The Intel Xeon Scalable CPU, whose model is not published, serves the storage appliance only.
It has 2 x 10GbE built in. The manual also lists an IPMI service port. OWC says up to 14 editors can connect over 10G or 1G, so more ports may exist on some configurations. It has no 2.5GbE, 5GbE or 25GbE ports, and no Thunderbolt, USB4 or OCuLink.
We cannot confirm it. Docker support is not published, and no container mention was found in several searches of the OWC site. That is an absence of evidence, not a stated no. The system runs the Jellyfish Manager appliance OS, whose underlying name is not published, and virtual machine support is also unconfirmed.
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 2 x 10GbE built in. The fastest port is 2 x 10GbE.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.