alt.freeweights.ocr / Unlimited-OCR-2-4bit

From:

mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.ocrSubject:

Unlimited-OCR-2-4bit

Date: 2026-11-15Commit: ac04b80Signed: 2DC28CC7B26A283B ✓

Image text to text model with 3.3B parameters. Safetensors weights, 2.63 GB in all. Published by mlx-community under MIT.

3.3B params

2.63GBUnlimited-OCR-2-4bitsafetensorspermissive

FactsParams3.3BSize2.63 GBFormatssafetensorsTaskimage text to textLicenseMITFrom sourcepermissive

$ fw get mlx-community/Unlimited-OCR-2-4bit
# manifest sha256 51832c32c328… · 2.63 GB · 25 files
$ fw verify ./Unlimited-OCR-2-4bit mlx-community/Unlimited-OCR-2-4bit

From sourceHosted (signed)mlx-community/Unlimited-OCR-2-4bitLast check: 2026-11-15 05:14 UTC

Run at home Get help

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

Quantized of Unlimited-OCR-2.

Works with

Run23 Fine-tune29 Convert15 Evaluate13 Scan13 Apps62

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 23

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 2.63 GB
Weights: 2.46 GB (safetensors)
Parameters: 3.3B
Formats: safetensors
Task: image text to text
License: MIT (permissive)
Files: 25, each with a sha256
Publisher: mlx-community
Added: 2026-11-15
Section: alt.freeweights.ocr

Lineage

Original release from the publisher.

Base model: baidu/Unlimited-OCR-2

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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 05:14 UTC	passed

Model card

From the publisher at commit ac04b80. Shown as plain text with links; images open at the publisher.

mlx-community/Unlimited-OCR-2-4bit#

baidu/Unlimited-OCR-2 converted to MLX with mlx-vlm: 4-bit affine quantization (group size 64) of the language model. The SAM and CLIP vision towers and the per-layer DASH router stay in bfloat16.

Refer to the original model card for details on the model.

Use with mlx-vlm#

Unlimited-OCR-2 support (page2d RoPE and DASH block-sparse attention) is being upstreamed to mlx-vlm. Until it is released, install from the branch that adds it:

pip install -U "git+https://github.com/shuuul/mlx-vlm.git"

# One page (gundam mode: 1024 global view + up to 16 local crops)
mlx_vlm.generate --model mlx-community/Unlimited-OCR-2-4bit --image page.png \
    --prompt "Multi page parsing." --max-tokens 8192 --temperature 0

# Several pages in one request (one 1024 base view per page)
mlx_vlm.generate --model mlx-community/Unlimited-OCR-2-4bit --image p1.png p2.png \
    --prompt "Multi page parsing." --max-tokens 16384 --temperature 0

The output uses <PAGE>, <BLOCK>label[x0, y0, x1, y1]<FORK>text and cross_* / append_* labels for blocks that continue across a page break; the upstream repository ships a converter to Markdown.

Files

25 files · 2.63 GBWeights 2.46 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 25 files with their sha256

File	Size	sha256
.gitattributes	1.75 KB	d4124e61a8f303cba079a549366987f2d162b3721d3f6bf0379a3287a8d0ebd7
README.md	1.50 KB	07076e896ec2a59f76b6c6d766095ff7c6f5a8c896df6f23d3f197c1fe67b671
_sparse_base_impl.py	222 KB	86da9c5638704bb9338575040568a97b3e10820bbeb426f51c07e866f3423ccd
assets/HarryPotter.gif	156 MB	572305c08be5a87c14b0c211d3ef28398a00818b341bfcfdb8152678bffa8ea5
assets/Unlimited-OCR2.png	1.08 MB	e231defdf9aebbf8d6cf6a6dc15ded22412629a2cbf196436e2d9b58973aa678
assets/leaderboard.png	1.48 MB	aca406f669dba1af337d7ac9b7be6dafad89b3afbf3570567c578b50dfeb9e8b
assets/logo.png	130 KB	e1c533934d3d5abaa1666c8ce858d4f2195b14471c7e3b8f3da772972359652d
chat_template.jinja	224 B	d46440846e0e99c13450d42551936db0624aa3fa390aee58be7c7463402d23a3
config.json	6.89 KB	76330cb407c8d1551e23f4259973274949244a04b009f5dd25ee66c954ebbe02
configuration_deepseek_v2.py	10.7 KB	b8470dd616ba8745fce6e27b093aef73a098863cc891b2477dcf9326a36000f7
conversation.py	9.25 KB	ec7b6ce89bcda643de1f43269ffa66a7b2e65dc3ed30e427958f776546b4ba03
dash_attention.py	71.5 KB	960b460acd816df8e561e73dccd5683acb95445eddc723c4f0d6ed1f462b2f77
deepencoder.py	37.9 KB	419b63388c1645b9b72c716070cdca36cd0be6047049424dc75941d3a00aaf1f
generation_config.json	111 B	dcd0479f3a12e5e4413d956197f8a4074408e4901834b38c7e036519134e05af
model.safetensors	2.46 GB	c623d9e83bf3f7035770beeb3110f57dc3ff4bf86e7ce871a858f840d329ed11
model.safetensors.index.json	78.4 KB	a9b6852a188b772155205f2321d47d863a79b121d267ba341077488ce606982e
modeling_deepseekv2.py	25.6 KB	24a15dfd47578ab24a7a4d4e977dc5d7a23dfef0a2a4c4bf73fcf3e2ce7acaf2
modeling_unlimitedocr.py	55.7 KB	f6df813cef23cc28b1daca40fd8cb20740d05a238e7b9dfa2334531fdcf39f1f
packing_patch.py	8.11 KB	e60d842c210c9f1d6cd2ae328cf9127a75f7941a0cea2a8e9abc14662f770c6c
processor_config.json	506 B	7dc5f3c9aab298f845c5664f276eca5692153654b0082067c3f295585fc89712
sparse_gather_e2e_triton.py	18.1 KB	58f1bc46093d47b00744970677e66bfbd7485a2d13810f46d13d867ceda13dd4
sparse_gather_triton.py	23.9 KB	c3de717ffaca40240c665b8d645f15a9d1999feeabaa94beb35caad877c2f0f4
special_tokens_map.json	549 B	9e89493d7938e7710c524dbaff613c3648f0a018262417af78505128004e5cb4
tokenizer.json	9.98 MB	c55c165e32c5a67830362a53e1f548c8930dcc8469efa30ff3252a982799c589
tokenizer_config.json	567 B	6835b63b4534bac1094a9f4e6b136b4569772b38b81d78cc773f3aa6e6b7aa47

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
ac04b80847 pinned now	2026-11-15 05:14 UTC	25 files · 2.63 GB

Use it

$ fw get mlx-community/Unlimited-OCR-2-4bit
# manifest sha256 51832c32c328… · 2.63 GB · 25 files
$ fw verify ./Unlimited-OCR-2-4bit mlx-community/Unlimited-OCR-2-4bit

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Unlimited-OCR-2-4bit.json --dir ./Unlimited-OCR-2-4bit
$ python3 fw.py verify ./Unlimited-OCR-2-4bit ./mlx-community__Unlimited-OCR-2-4bit.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Unlimited-OCR-2-4bit --revision ac04b808479927cc42ea82e06f55ebecd2b0a623 --local-dir ./Unlimited-OCR-2-4bit

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/Unlimited-OCR-2-4bit", revision="ac04b808479927cc42ea82e06f55ebecd2b0a623")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/Unlimited-OCR-2-4bit", revision="ac04b808479927cc42ea82e06f55ebecd2b0a623", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Unlimited-OCR-2-4bit --revision ac04b808479927cc42ea82e06f55ebecd2b0a623

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: 07076e896ec2a59f76b6c6d766095ff7c6f5a8c896df6f23d3f197c1fe67b671
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.ocrSubject: Unlimited-OCR-2-4bitDate: 2026-11-15Commit: ac04b80Signed: 2DC28CC7B26A283B ✓

Upstream: mlx-community/Unlimited-OCR-2-4bit
Pinned commit: ac04b808479927cc42ea82e06f55ebecd2b0a623
Manifest: Unlimited-OCR-2-4bit.json · .minisig
Manifest sha256: 51832c32c328004235e78a622f145dc1271cf3e27d7b3b8405a2b11a751ddb59
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:14 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Unlimited-OCR-2-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Unlimited-OCR-2-4bit.json.minisig
$ minisign -Vm Unlimited-OCR-2-4bit.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

baidu/Unlimited-OCR-2 · 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/Unlimited-OCR-2-4bit

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. Unlimited-OCR-2-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/Unlimited-OCR-2-4bit

Related models

All of alt.freeweights.ocr →

From:

mlx-community <huggingface.co/mlx-community>Subject: Unlimited-OCR-2-6bit

From:

mlx-community <huggingface.co/mlx-community>Subject: Unlimited-OCR-2-8bit

From:

baidu <huggingface.co/baidu>Subject: Unlimited-OCR-2

Unlimited-OCR-2-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/Unlimited-OCR-2-4bit#

Use with mlx-vlm#

Files

Use it

License

Provenance

How to verify

Model tree

Related models