CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / olmOCR-2-7B-1025-mlx-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

olmOCR-2-7B-1025-mlx-8bit

Date: 2026-11-14Commit: b0f72c9Signed: 2DC28CC7B26A283B ✓

Image text to text model. Safetensors weights, 9.46 GB in all. Published by mlx-community under Apache-2.0.

qwen9.46GBolmOCR-2-7B-1025-mlx-8bitsafetensorspermissive
FactsParamsnot statedSize9.46 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/olmOCR-2-7B-1025-mlx-8bit
# manifest sha256 6e8709085679… · 9.46 GB · 18 files
$ fw verify ./olmOCR-2-7B-1025-mlx-8bit mlx-community/olmOCR-2-7B-1025-mlx-8bit
From sourceHosted (signed)mlx-community/olmOCR-2-7B-1025-mlx-8bitLast check: 2026-11-14 21:30 UTC
Run at homeGet help

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

Quantized of Qwen2.5-VL-7B-Instruct.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
9.46 GB
Weights
9.45 GB (safetensors)
Parameters
not stated
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
18, each with a sha256
Publisher
mlx-community
Added
2026-11-14
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-VL-7B-Instruct

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.co2026-11-14 21:30 UTCpassed

Model card

From the publisher at commit b0f72c9. Shown as plain text with links; images open at the publisher.

mlx-community/olmOCR-2-7B-1025-mlx-8bit#

This model was converted to MLX format from allenai/olmOCR-2-7B-1025 using mlx-vlm version 0.3.5. Refer to the original model card for more details on the model.

Use with mlx#

pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/olmOCR-2-7B-1025-mlx-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

18 files · 9.46 GBWeights 9.45 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 18 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md621 B7cf336ecda9d906a12284890f54f4301af8ce56e4b865c98964a68436ede1044
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
chat_template.jinja1.02 KBa0bc6f6fc7a29a80017a433e8f03a1cc1236e838a944a2d034295a60c4f2fddb
chat_template.json1.05 KBad60d90252ed0b0705ba14e2d0ad0fec0beac1ea955642b54059b36052d8bc96
config.json9.06 KB9f3068a72bed1d328326be3623701b280ad5b8ffd6995d39ec5e1cdc5bb5f799
generation_config.json260 Bf8f9e40b9d85636128865f0be3c696b915932049b6c25b087241f63f5ef4e785
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00002.safetensors5.33 GB7078b086bf1545e8f5382287ef5554d611349f7ba8ef7fa90a818666cc63cab4
model-00002-of-00002.safetensors4.12 GB36239bb0581f60fd14068592fb250066b38c61d025442af3a421b83516d878e9
model.safetensors.index.json57.7 KB4be35310ddc165e46e88de4c3fec8c1210014b0b8717f4544d82cc740814ae0c
preprocessor_config.json829 Bdfc7263fe735989c65c290d394198c4724d5afc58bf15c815d5e2e25b00b51b1
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MB9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
tokenizer_config.json4.73 KBe04be4dd17e9f661bc487ba848a37f66a8f1adf2eef412f5d4ecb40cab4d39e7
video_preprocessor_config.json955 B9b7003dd088dd6cd924a7ba9c5fcfea865063adad5dcdc4080ac9c7264e1fe78
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
zero_to_fp32.py33.3 KBe8a2553b434ac043ec63b022db1e768277acf8d4e70f10a2842db6d238977135
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
b0f72c9dfd pinned now manifest updated, same commit2026-11-14 21:30 UTC18 files · 9.46 GB
b0f72c9dfd2026-11-14 21:30 UTC18 files · 9.46 GB

Use it

$ fw get mlx-community/olmOCR-2-7B-1025-mlx-8bit
# manifest sha256 6e8709085679… · 9.46 GB · 18 files
$ fw verify ./olmOCR-2-7B-1025-mlx-8bit mlx-community/olmOCR-2-7B-1025-mlx-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/olmOCR-2-7B-1025-mlx-8bit.json --dir ./olmOCR-2-7B-1025-mlx-8bit $ python3 fw.py verify ./olmOCR-2-7B-1025-mlx-8bit ./mlx-community__olmOCR-2-7B-1025-mlx-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/olmOCR-2-7B-1025-mlx-8bit --revision b0f72c9dfdb5488691e3c00d2afa2613c16c3bb3 --local-dir ./olmOCR-2-7B-1025-mlx-8bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("mlx-community/olmOCR-2-7B-1025-mlx-8bit", revision="b0f72c9dfdb5488691e3c00d2afa2613c16c3bb3") model = AutoModelForImageTextToText.from_pretrained("mlx-community/olmOCR-2-7B-1025-mlx-8bit", revision="b0f72c9dfdb5488691e3c00d2afa2613c16c3bb3", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/olmOCR-2-7B-1025-mlx-8bit --revision b0f72c9dfdb5488691e3c00d2afa2613c16c3bb3
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
README.md
Text sha256
7cf336ecda9d906a12284890f54f4301af8ce56e4b865c98964a68436ede1044
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: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject: olmOCR-2-7B-1025-mlx-8bitDate: 2026-11-14Commit: b0f72c9Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/olmOCR-2-7B-1025-mlx-8bit
Pinned commit
b0f72c9dfdb5488691e3c00d2afa2613c16c3bb3
Manifest
olmOCR-2-7B-1025-mlx-8bit.json · .minisig
Manifest sha256
6e87090856798a8582ceb79f19fb7265b1390812d8c8af7ab2b71e8d42190137
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:30 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/olmOCR-2-7B-1025-mlx-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/olmOCR-2-7B-1025-mlx-8bit.json.minisig $ minisign -Vm olmOCR-2-7B-1025-mlx-8bit.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

Qwen/Qwen2.5-VL-7B-Instruct · 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 mlx-community/olmOCR-2-7B-1025-mlx-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. olmOCR-2-7B-1025-mlx-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/olmOCR-2-7B-1025-mlx-8bit

Related models

All of alt.freeweights.qwen →
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF