CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / dots.ocr-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.textSubject:

dots.ocr-GGUF

Date: 2026-11-15Commit: 2c093a3Signed: 2DC28CC7B26A283B ✓

Model. Gguf weights, 9.33 GB in all. Published by ggml-org under MIT.

text9.33GBdots.ocr-GGUFggufpermissive
FactsParamsnot statedSize9.33 GBFormatsggufTasknot taggedLicenseMITFrom sourcepermissive
$ fw get ggml-org/dots.ocr-GGUF
# manifest sha256 8c1eceee5b32… · 9.33 GB · 6 files
$ fw verify ./dots.ocr-GGUF ggml-org/dots.ocr-GGUF
From sourceHosted (signed)ggml-org/dots.ocr-GGUFLast check: 2026-11-15 04:42 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of dots.ocr.

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
9.33 GB
Weights
1.89 GB (smallest of 2 GGUF variants)
Parameters
not stated
Formats
gguf
Task
not tagged
License
MIT (permissive)
Files
6, each with a sha256
Publisher
ggml-org
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: dots-studio/dots.ocr

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 04:42 UTCpassed

Model card

From the publisher at commit 2c093a3. Shown as plain text with links; images open at the publisher.

dots.ocr-GGUF#

Original model: https://huggingface.co/rednote-hilab/dots.ocr

Related PR: https://github.com/ggml-org/llama.cpp/pull/17575

Files

6 files · 9.33 GBWeights 1.89 GB (smallest of 2 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 6 files with their sha256
FileSizesha256
.gitattributes1.75 KBb98366e2fd9fbf07763840b46843d993b6aceb6d28e7c6fe6c5c164c468ba3e6
README.md199 B34ba8d67744e1b7a4087e07603f5a53b7fdfcd5c4a5030972e9d39830ad90ae3
dots.ocr-Q8_0.gguf1.89 GB6f2db1a75215893760b7c7185d52f11715d2e0cb7bff9cefd3f6d409fa1de7e9
dots.ocr-f16.gguf3.56 GB2bb30df3e055fb8cf9b643677d3e164f68f184a70b8c8c439ac67e9bd0b409e8
mmproj-dots.ocr-Q8_0.gguf1.34 GB20d3d35bea3a64ead0b4b213f8db0de136e174bb5b75b8e85786c51e8e822423
mmproj-dots.ocr-f16.gguf2.53 GBf462429dbf41729379df4252f84331c9646d80e53f092ccccfd2cb922a3b544e
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
2c093a32ca pinned now2026-11-15 04:42 UTC6 files · 9.33 GB

Use it

$ fw get ggml-org/dots.ocr-GGUF
# manifest sha256 8c1eceee5b32… · 9.33 GB · 6 files
$ fw verify ./dots.ocr-GGUF ggml-org/dots.ocr-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/ggml-org/dots.ocr-GGUF.json --dir ./dots.ocr-GGUF $ python3 fw.py verify ./dots.ocr-GGUF ./ggml-org__dots.ocr-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/dots.ocr-GGUF --revision 2c093a32ca360a396bc6d87d60408636130b9d9b --local-dir ./dots.ocr-GGUF
llama.cppDownload one GGUF variant (dots.ocr-Q8_0, 1.89 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/dots.ocr-GGUF --include "dots.ocr-Q8_0*" --local-dir ./dots.ocr-GGUF $ llama-server -m ./dots.ocr-GGUF/dots.ocr-Q8_0.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./dots.ocr-GGUF/dots.ocr-Q8_0.gguf\n' > Modelfile $ ollama create dots.ocr-gguf -f Modelfile
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
34ba8d67744e1b7a4087e07603f5a53b7fdfcd5c4a5030972e9d39830ad90ae3
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.textSubject: dots.ocr-GGUFDate: 2026-11-15Commit: 2c093a3Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/dots.ocr-GGUF
Pinned commit
2c093a32ca360a396bc6d87d60408636130b9d9b
Manifest
dots.ocr-GGUF.json · .minisig
Manifest sha256
8c1eceee5b32691ac8b040bad24606acf7a65c510ce0a5175134ef6a01199b6c
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:42 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/dots.ocr-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/dots.ocr-GGUF.json.minisig $ minisign -Vm dots.ocr-GGUF.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

dots-studio/dots.ocr · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/dots.ocr-GGUF
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. dots.ocr-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/dots.ocr-GGUF

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B