Tensor ArchiveAI
Download

Tensor Archive Local · FAQ & product guide

Keep related models together. Recover every byte.

Tensor Archive keeps checkpoints, adapters and related model versions together while reducing their combined footprint. Every archived version remains available for exact recovery.

  • 01 Local by default
  • 02 Exact restore
  • 03 No account required
Jump to 01 Quick start 02 Storage numbers 03 Sources & adapters 04 Verify and recover 05 Good use cases 06 Current limits 07 Privacy & license
01 / Quick start

Start with a real public family or your own folder.

On an empty Overview, select Build real public family. Tensor Archive downloads a fixed BERT Tiny sample and opens the measured result. The reference run represented 72,640,943 logical bytes in 17,178,128 stored bytes: 76.35% less space. Results can change if the published sample changes in a later release.

The sample downloads only declared files from public Hugging Face repositories; it never executes model code or weights. If you are offline, choose Use offline synthetic demo. The separate Google BERT Tiny preset remains a single-checkpoint compatibility check and is expected to show limited savings.

  1. 1
    Build the public family

    Choose Build real public family to open a measured sample and review its storage result.

  2. 2
    Or select Add model family

    From Overview, choose Local folder, then use Choose folder.

  3. 3
    Analyze before writing

    Select Analyze source. Review the detected type, source size and expected result.

  4. 4
    Name and archive

    Give the family a clear archive name and select Archive folder. Progress appears as a local job.

  5. 5
    Verify, then test a restore

    Open the family, run Verify, restore a version, and compare or open it before deleting any source copy.

Safe default

Archiving creates a managed copy; it does not move or delete your source. Keep the original until Verify succeeds and you have tested an exact restore.

02 / Read the dashboard

Understand what each storage number means.

Tensor Archive separates the size your versions represent from the bytes physically required to keep them.

Logical size Every version in full

The total size if each archived version were kept as its own self-contained copy.

Stored size Physical bytes used

The bytes currently occupied by the family inside Tensor Archive's local storage.

Space reclaimed Logical minus stored

The difference between the full represented size and the disk space currently used.

Additional storage Space used by this addition

The extra disk space used when a new version is added to the archive.

About “up to 76% less”

76.35% is the public BERT Tiny demo result. A separate larger reference family measured 71.2%. A same-shape public suite also measured DistilBERT at 76.46% and SmolLM2-135M at 76.33%, with exact restoration in all twelve cases. None is a promise for every folder: families that share substantial content can save a lot; unrelated or already compressed files may save little.

03 / Organize related versions

Keep versions from the same project together.

Clear grouping makes storage results easier to understand and each version easier to find when you need it.

Local folders

Checkpoints and model directories

Choose a folder using the native system picker. Tensor Archive receives temporary access to that selection, checks it locally and rejects unsafe links or special files.

Adapters

Attach a LoRA to its archived base

Add the main checkpoint and its adapters to the same family. Tensor Archive guides you when it needs confirmation before continuing.

Hugging Face

Resolve a public repository revision

Enter owner/model and a branch, tag or commit. Analyze reads the public file inventory and may inspect a small adapter configuration; it does not download or execute model weights. Archive then resolves an immutable commit and stores the complete public snapshot locally. The Google BERT Tiny preset offers a small official first source.

Best practice

Use one family for genuinely related models

Group a base, its adapters and its real revisions together. Separate unrelated architectures or projects so that each archive stays clear.

04 / Work with an archived version

Inspect, prove and recover what you saved.

Verify
Confirms stored-byte integrity

Creates a durable receipt showing that the saved version can be recovered exactly. It does not assess model quality or accuracy.

Restore
Recovers the selected version exactly

Creates a byte-for-byte output in the app's local restore area.

Download
Saves a recovery copy

When the job completes, save the copy to Downloads without overwriting an existing file.

Inspect
Shows what a version contains

Review its files, sizes and checksums before restoring it.

Activity
Keeps the operational record

Archive, verify and recovery actions run locally with progress, status and completion receipts.

Storage
Shows the space in use

Review managed storage and generated recovery outputs. Copies already saved to Downloads are outside the app and are not counted.

Delete
Removes one family safely

Removes that family's managed data while leaving existing copies in Downloads untouched.

05 / Reclaim space safely

Delete originals only after you prove recovery.

Tensor Archive deliberately does not remove source data. That final storage decision stays with you.

1Archive the folder and wait for successful completion.

2Verify the archived version and retain its receipt.

3Restore it to a separate output and confirm your workflow can use it.

4Back it up externally if loss of this Mac would matter.

5Delete the old source manually only when you are satisfied with those checks.

One Mac is not a backup

Local archiving saves disk space, but it does not protect against disk failure, theft or accidental removal of the application data directory. Keep another copy of irreplaceable model data.

06 / Product fit

Where Tensor Archive is most useful today.

Use it for
  • A base model with several LoRAs or adapters.
  • Related checkpoints and training revisions.
  • Comparing the disk space used by related versions.
  • Freeing local SSD space after verified recovery tests.
  • Auditing archived files and recovery receipts.
  • Exact offline restores from a local archive.
It is not
  • A training or inference accelerator.
  • Quantization, pruning or a model conversion tool.
  • A way to improve model quality or accuracy.
  • A guaranteed 76% saving for every collection.
  • A cloud backup or multi-device sync service in this release.
  • A replacement for an independent backup of important data.
Current product scope

Tensor Archive Local supports Apple silicon Macs running macOS 13 or later, x64 PCs running Windows 10 22H2 or Windows 11 and x64 PCs running Ubuntu 24.04. Integrated workflows for LM Studio, Ollama, FLUX and ComfyUI are available. Public Hugging Face repositories and local folders are also available. Private repository authentication, S3, cloud sync and team libraries are not available yet.

07 / Privacy, access and updates

Your local models stay local.

Privacy

No account is required

Local folders and archive contents are not uploaded to Tensor Archive. Network access is used when you explicitly choose Hugging Face and when the app checks tensorarchive.ai for product updates. Anonymous product analytics are enabled by default and can be disabled under Settings.

Anonymous analytics

Usage signals, never model data

Tensor Archive records app opens, active time, the operation used, its outcome, app version, platform and update results under a separate random analytics identifier. It never sends model weights or archive contents, model, repository or file names, local paths, hashes, email or license identity. Raw events are kept for at most 90 days. Turning analytics off requests deletion of this installation's events.

Local data

One private application directory

Archived content, receipts and generated outputs live under ~/Library/Application Support/ai.tensorarchive.local/ on macOS, %LOCALAPPDATA%\ai.tensorarchive.local on Windows or ~/.local/share/ai.tensorarchive.local/ on Linux. Removing the matching directory removes the local archive too.

License

A protected 14-day trial or Local Pro

Each installation can start one free 14-day trial without a card or account. Viewer, Verify and Restore remain available afterward; creating or extending families requires an active trial or Local Pro and an internet connection. Open License in the app to buy Local Pro for $199 USD through Stripe Checkout and activate up to three machines. Stripe processes the live payment; Tensor Archive never receives card details.

Updates

Verified update metadata

The app validates the signed update manifest and exact SHA-256 before offering a new version. If an older installation cannot update automatically, download the current installer from the official Tensor Archive page and install it once.

Ready to try it?

Start with one related model family.

Archive it, verify it and test the restore before changing your existing folders.

Free Download Return to Tensor Archive