Skip to content
Is there an AI for this?

Use case

Local LLM

Running an open-weight model on hardware you own — a workstation, a GPU server, a laptop. The question is usually which model fits the memory you have and how many people can use it at once.

Source
Editorial ontology entry — no fetched document behind this page
Evidence
none on this page — it links to the pages that hold it
Category
Infrastructure
Typical risk
medium
Entry
editorial · reviewed 25 Aug 2026

01What this is

A local LLM deployment downloads open-weight models and serves them from your own machine through an inference server. Practical model choice is set by memory: weights in the chosen quantisation, plus the KV cache for the context length and the number of concurrent users.

A good deployment sizes hardware from the workload rather than the model name, picks a quantisation deliberately, pins model versions, measures tokens per second at the intended concurrency, and keeps a fallback path for peaks. Model licences are checked before commercial use — open weights are not automatically open licences.

Pitfalls: buying a GPU before measuring; a 70B model chosen for a task a 14B handles; and an inference server run as a single point of failure with no monitoring. Weights are downloaded once from a registry over the network — that is normally the only external traffic, and it is worth stating explicitly.

Typical data
internal documents, source code, client documents
Solution classes it admits
Self-hosted

02Deployment options

  • ASSESSMENT

    On a neutral reading of this use case, Self-hosted is a strong alternative, Private cloud is a strong alternative and Enterprise SaaS is conditional.

  • ASSESSMENT

    Read as a generic reading of this page, not a recommendation: no organisation, size, jurisdiction, budget or technical capability has been supplied, so wherever an option depends on one of those, it says "unknown". Ask your own question to get a verdict that accounts for them.

Private cloud

STRONG ALTERNATIVE

Managed model API or private model deployment in your cloud account

  • ASSESSMENT

    Two patterns fit inside one account in a region you name: call a managed foundation-model API such as Amazon Bedrock, Microsoft Foundry / Azure OpenAI, or Vertex AI; or deploy an open-weight model on GPU compute you control. Your application, retrieval layer, storage, identity and logs remain in your cloud boundary in both patterns.

  • ASSESSMENT

    The managed-API pattern can use closed-source frontier models without buying or operating GPUs. It is usually the fastest way to build a custom workflow, but prompts and retrieved context are processed by the managed service, so model availability, retention, abuse monitoring and regional routing must be checked for the exact feature and endpoint.

  • ASSESSMENT

    The private-model pattern gives more control over weights, serving and network paths, and can use managed endpoints or your own containers. It also makes your team responsible for capacity, patches, model upgrades, evaluation and failover.

  • ASSESSMENT

    The cloud provider becomes a data processor in either pattern: you need a DPA, a documented region, and an answer on cross-region routing and where support staff can access the environment from.

  • RECOMMENDATION

    Start with the managed-API pattern when the workflow is custom but model operations are not the source of competitive advantage; move to private model serving only if evaluation, volume, portability or the data boundary justifies the extra operations. Your stated technical capability is "unknown".

Self-hosted

STRONG ALTERNATIVE

Open-weight models on infrastructure you operate

  • ASSESSMENT

    Documents, queries and embeddings stay on machines you own, using an open-weight model whose licence you review. For a brief that involves confidential documents, that removes a model-API vendor from the data path rather than governing that transfer by contract.

  • ASSESSMENT

    It costs you the operational work instead: a GPU server, Docker, Linux, backups and a patching routine. Your stated technical capability is "unknown", which is the attribute this option most depends on.

  • ASSESSMENT

    No processor agreement, subprocessor list or cross-border transfer assessment is needed for the model itself, because no third party processes the content.

  • RECOMMENDATION

    Recommended where local processing is preferred (you did not say so) and the content is sensitive (confidential documents).

Enterprise SaaS

CONSIDER IF

Finished closed-source cloud product with enterprise controls

  • ASSESSMENT

    This is a complete vendor application, not a model API: examples include an enterprise assistant, coding copilot or document product with the workflow, interface, connectors and administration already built. It can use closed-source cloud models while requiring no model hosting or application engineering from your team.

  • RECOMMENDATION

    Choose it when the product already performs the actual workflow and its controls meet your requirements. Do not choose it only because its underlying model is strong: a finished SaaS product is less flexible than building against a managed API when your process, integrations or review steps are organisation-specific.

  • ASSESSMENT

    Vendor commitments are treated as unverified until we have fetched the page that makes them. Until then this option carries questions to ask, not assurances: a signed data processing agreement covering the data you will actually put in; a documented data residency commitment naming the region, in the contract rather than a blog post; a written no-training commitment for your content, including uploads and connected sources; stated retention periods and a deletion path you can exercise; an administrative audit log you can export, and SSO with group-based access control.

  • RECOMMENDATION

    No jurisdiction was named, so this is the check rather than the conclusion: compare the vendor's stated processing locations and subprocessor list against the cross-border transfer rules wherever you operate before uploading anything.


03Deployment stacks

2 published

04Tools by hosting option

11 tools

Self-hosted11

Private cloud9

Vendor cloud2

On-premise (enterprise plan)4


05Compliance hot spots

This use case usually raises open-source licensing, model access, security, intellectual property, confidentiality, logging, personal data, prompt leakage, retention, transparency.

Open-source licensing
No published jurisdiction page names this topic yet
Model access
No published jurisdiction page names this topic yet
Intellectual property
No published jurisdiction page names this topic yet
Confidentiality
Hong KongTaiwan
Personal data
JapanTaiwan
Prompt leakage
Hong KongJapan
Retention
Hong Kong

06Example questions

Each of these opens the question box with the text already in it. The answer is researched for your organisation, not for this page.

  1. 01Run an open-weight model on our own GPU server.
  2. 02What hardware do we need to run a 32B model for 40 people?
  3. 03Set up a local LLM that works without internet access.

Improve this page

Sign in to contribute

From the field

0 deployments · 0 questions

Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.