document imports, parsing/OCR, embedding batches, retrieval queries and simultaneous model calls Time the job and identify CPU, storage or external-service waits before replacing hardware.
Imports, processing and simultaneous users.ナレッジグラフ抽出ツールのハードウェア要件:RAM、CPU、ストレージ、ドキュメント取り込み、AIバックエンド
Plan Knowledge Graph ExtractorのRAM、CPU、永続ストレージ、サービスの依存関係を抽出し、ワークロードに応じたZimaOSの必要スペック、バックアップ、実用的なハードウェアの選択肢を提案します。
Knowledge Graph Extractor hardware requirements at a glance
Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget.
- RAM
- App and inference worker have independent host-memory budgets; GPU VRAM is not interchangeable with system RAM.
- CPU
- The documented model worker uses an NVIDIA L4 with 24 GB VRAM; qualify that separate backend.
- Storage
- The documented setup downloads roughly 17 GB model artifacts; add documents, extracted state, images and backups.
- Required services
- Use the documented Knowledge Graph Extractor runtime and selected service topology. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget.
- Main sizing variable
- document imports, parsing/OCR, embedding batches, retrieval queries and simultaneous model calls
- Practical Zima starting point
- Conditional lab, data-storage or supporting-service hardware only; a complete production deployment requires a separately verified host meeting the upstream requirements. Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker.
From official requirements to the right setup
Plan the complete Knowledge Graph Extractor workload before selecting a server.
-
Official requirements
Choose the exact edition, stable release and supported container/runtime. Use the documented Knowledge Graph Extractor runtime and selected service topology. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget.
-
Confirm your needs
Test a representative busy operation: document imports, parsing/OCR, embedding batches, retrieval queries and simultaneous model calls Record peak resident memory, CPU, disk latency and completion time, including other containers.
-
Leave room to grow
Place active state on reliable persistent storage. Persist original documents, parsed content, embeddings/indexes, application database and model configuration. Budget working space for an upgrade or import and test recovery before relying on the deployment.
-
Run it on ZimaOS
Follow the supported upstream runtime, operating system and complete service topology for the selected release. On ZimaOS, consider Custom Install only when a maintained compatible amd64 image and every required host capability have been verified. Otherwise use a separately supported Linux environment; this guide does not certify an unverified container deployment. Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker.
Check every playback client
- Exact edition and stable release
- Supported upstream runtime and architecture
- All required companion services
- Realistic peak activity
- Persistent data and file ownership
- Free host ports and reachable URLs
- Working space and backup retention
- Successful database/file restore
Official minimum requirements
Reviewed November 20, 2026 against the linked upstream deployment documentation. Numerical values retain their stated minimum, recommendation or example scope; select release-compatible instructions before installation.
Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker. Numerical examples above retain their stated deployment scope; co-hosted services and independent backups need additional capacity.
| Requirement | Official minimum | What this supports |
|---|---|---|
| RAM guidance | App and inference worker have independent host-memory budgets; GPU VRAM is not interchangeable with system RAM. | Official guidance keeps its original test, recommendation or example scope. |
| CPU guidance | The documented model worker uses an NVIDIA L4 with 24 GB VRAM; qualify that separate backend. | Core counts do not predict a fixed user, device or document capacity. |
| Storage planning | The documented setup downloads roughly 17 GB model artifacts; add documents, extracted state, images and backups. | Installation space is separate from retained content, working files and backups. |
| Service topology | Use the documented Knowledge Graph Extractor runtime and selected service topology. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. | Include every stateful companion service in the host budget. |
| Persistent state | Persist original documents, parsed content, embeddings/indexes, application database and model configuration. | An image rebuild or container replacement is not a backup. |
| Deployment boundary | Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker. | Check the linked project instructions for the selected edition and release. |
When to upgrade your hardware
Use observed Knowledge Graph Extractor workload pressure to decide when an upgrade is warranted.
Busy operations exceed the available window
The complete stack runs short of memory
Persistent data approaches available capacity
Inspect the application and each required service for OOM events, sustained swap or growing queues. Reduce unnecessary concurrency before adding capacity.
Shared hosts and background work.Persist original documents, parsed content, embeddings/indexes, application database and model configuration. Track primary state and backup retention separately.
Long-lived installations and growing collections.Plan hardware growth with confidence
Address storage, memory, compute and deployment limits separately.
Use suitable active storage
Put latency-sensitive application/database state on durable local SSD storage and keep recoverable copies.
SATA or PCIe SSD according to measured data growth.Add memory for the complete stack
Choose a higher-RAM host when peak application and companion-service usage leaves inadequate OS headroom.
ZimaBoard 2 1664 or ZimaCube 2 Pro according to the measured constraint.Separate capacity from compute
A multi-drive system helps when retained content and backup storage are the problem; it is not automatically a faster application.
ZimaCube 2 when a broader multi-drive workload justifies it.Fix the observed bottleneck
Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker.
Check service configuration, I/O and network behavior before selecting a stronger CPU.Can it run on ZimaOS?
Follow the supported upstream runtime, operating system and complete service topology for the selected release. On ZimaOS, consider Custom Install only when a maintained compatible amd64 image and every required host capability have been verified. Otherwise use a separately supported Linux environment; this guide does not certify an unverified container deployment.
Verify the supported upstream deployment
Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker. Follow the supported upstream runtime, operating system and complete service topology for the selected release. On ZimaOS, consider Custom Install only when a maintained compatible amd64 image and every required host capability have been verified. Otherwise use a separately supported Linux environment; this guide does not certify an unverified container deployment.
Review upstream deployment guidance ↗Use the official Knowledge Graph Extractor deployment instructions
Keep the selected stable release, persistent paths and companion services aligned with upstream documentation.
Review Knowledge Graph Extractor official installation ↗Check workload-specific deployment details
Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker.
Review Knowledge Graph Extractor deployment details ↗Which Zima hardware fits Knowledge Graph Extractor?
Conditional lab, data-storage or supporting-service hardware only; a complete production deployment requires a separately verified host meeting the upstream requirements.
Which workload best matches your Knowledge Graph Extractor deployment?
Conditional lab, data-storage or supporting-service hardware only; a complete production deployment requires a separately verified host meeting the upstream requirements. Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker.
- Supporting hardware onlyZimaBoard 2 1664
These are practical workload recommendations, not official app requirements, compatibility certification, measured capacity limits or performance guarantees. Include all co-hosted services and independent backups.
| Zima hardware | Best for | Example workload | Core configuration | Recommended boundary | Next step |
|---|---|---|---|---|---|
| ZimaBoard 2 1664 | Conditional lab or supporting-service role | document imports, parsing/OCR, embedding batches, retrieval queries and simultaneous model calls |
|
Conditional lab, data-storage or supporting-service hardware only; a complete production deployment requires a separately verified host meeting the upstream requirements. Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker. | Get Now |
| ZimaCube 2 Pro | Conditional lab or supporting-service role | Use the documented Knowledge Graph Extractor runtime and selected service topology. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. |
|
Conditional lab, data-storage or supporting-service hardware only; a complete production deployment requires a separately verified host meeting the upstream requirements. Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker. | Get Now |
What the Press Says
Highlights from trusted reviewers worldwide.
“ZimaCube 2: Not just another NAS, tested with 25TB storage, local AI agents, 4K transcoding, and real homelab workflows.”Read full review
“The ZimaBoard 2 is a compact x86 server board that can be turned into a mini NAS, home server, media box, or self-hosting hub.”Read full review
“ZimaCube 2: A modern, high-performance NAS with plenty of room to grow—built for users who want more than basic storage.”Read full review
“Coverage focused on ZimaCube 2's open hardware foundation, no monthly fee, and self-hosting flexibility.”Read full review
Loved by the Community
Stories and reviews from people who build with Zima every day.
Zima Blade Little yet Powerful
Maybe I am not digital natives but I live with PCs since 12 years old in 1984 when IBM PC clone come to my home. Many years have passed and many operating system I've tried. For me Zima blade and CasaOS was a quantum leap for home PC enthusiast and server lab machine to make me stay curious and relevant for this era.
Very good!!
I use ZimaCube Pro as 5th Proxmox cluster node. It runs several VMs and containers, including a VM with GPU passthrough to run a self-hosted LLM. A specific LXC container runs a Samba server for NAS capabilities using four of six RAID 6 SATA HDDs with ZFS.
Great innovation for mini server!
It is very useful and makes a powerful mini server for many purposes, including university and college students in engineering and electronics. Thank you so much for making this server.
Avaliação ZimaBoard 2
Construí um servidor de uso pessoal. O desempenho está muito bom e funciona perfeitamente onde quer que eu esteja. A surpresa é não dependermos de grandes estruturas para termos nosso próprio servidor de dados. Como iniciante, estou gostando bastante do ZimaOS, pois ele é simples e eficiente.
Frequently asked questions
Answers to Knowledge Graph Extractor RAM, CPU, storage, Docker, database and ZimaOS sizing questions.
How much RAM should I plan for Knowledge Graph Extractor?
App and inference worker have independent host-memory budgets; GPU VRAM is not interchangeable with system RAM. Include ZimaOS, the application and its companion services rather than reserving the entire machine for one container.
What drives the CPU requirement?
The documented model worker uses an NVIDIA L4 with 24 GB VRAM; qualify that separate backend. The workload to test is: document imports, parsing/OCR, embedding batches, retrieval queries and simultaneous model calls
Which data must survive a container update?
Persist original documents, parsed content, embeddings/indexes, application database and model configuration. Preserve a consistent database/file set and verify that your recovery procedure restores a working application.
What other services belong in the budget?
Use the documented Knowledge Graph Extractor runtime and selected service topology. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget.
Does this workload need a dedicated GPU?
Accelerator needs depend on the selected inference, synthesis, browser or media backend. Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker.
Can I deploy it on ZimaOS?
Follow the supported upstream runtime, operating system and complete service topology for the selected release. On ZimaOS, consider Custom Install only when a maintained compatible amd64 image and every required host capability have been verified. Otherwise use a separately supported Linux environment; this guide does not certify an unverified container deployment. Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker.
What should I check before upgrading hardware?
Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker. Measure the same representative operation before and after a configuration or hardware change.
Which Zima device is a practical starting point?
Conditional lab, data-storage or supporting-service hardware only; a complete production deployment requires a separately verified host meeting the upstream requirements. Document ingestion and graph extraction using a separately provisioned model worker. Ingestion, parsing/OCR, embeddings, retrieval storage and generation have separate working sets. Dataset size, re-indexing and concurrent questions change peaks. A remote provider or independently hosted model is not included in the application-server memory budget. The documented model worker uses an NVIDIA L4 with 24 GB VRAM and roughly 17 GB of downloaded model artifacts. A compact NAS may supply verified storage/control services, but is not a certified substitute for that GPU worker.
What sources informed this Knowledge Graph Extractor hardware guide?
This guide was reviewed against the linked project deployment documentation on November 20, 2026. Zima device choices are editorial workload guidance, separate from upstream requirements and measured performance.


