CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Unlimited-OCR-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject:

Unlimited-OCR-4bit

Date: 2026-11-15Commit: 945968cSigned: 2DC28CC7B26A283B ✓

Image text to text model with 3.3B parameters. Safetensors weights, 2.46 GB in all. Published by mlx-community under MIT.

3.3B params2.46GBUnlimited-OCR-4bitsafetensorspermissive
FactsParams3.3BSize2.46 GBFormatssafetensorsTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get mlx-community/Unlimited-OCR-4bit
# manifest sha256 0465d6a3267c… · 2.46 GB · 15 files
$ fw verify ./Unlimited-OCR-4bit mlx-community/Unlimited-OCR-4bit
From sourceHosted (signed)mlx-community/Unlimited-OCR-4bitLast check: 2026-11-15 05:17 UTC
Fine-tune in StudioGet help

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

Quantized of Unlimited-OCR.

Runs withAIBrixBentoMLCTranslate2ExLlamaV2ExLlamaV3exofastllmFlashInferKTransformersLitServeLMCacheLMDeployLocalAImistral.rsMLC LLMMooncakeSGLangText Generation WebUItinygradTransformersTriton Inference ServervLLMXinferenceFine-tune withAccelerateAlignment HandbookAxolotlColossal-AIDeepSpeedEasyR1FlashAttentionH2O LLM StudioJAXKerasLiger KernelLitGPTLLaMA-FactoryMegatron-LMms-swiftnanotronOLMo-coreOpenRLHFOumiPEFTPyTorch Lightningsd-scriptsSimpleTunerTorchTitantorchtuneTransformer EngineTRLUnslothverlConvert withAQLMAutoRoundCore ML ToolsExecuTorchGPTQModelLLM CompressormergekitNeural CompressorOliveONNXOptimum QuantoOptimumsafetensorsTensorRT Model OptimizertorchaoEvaluate withAutoevalsDeepEvalEvaluateHELMLightEvallm-evaluation-harnessOpenCompassOpikRagassimple-evalsSWE-benchTruLensWeaveScan withAgentDojoAI Fairness 360DeepTeamDetoxifyFairlearngarakGiskardGuardrailsMCP ScannerModelScanNeMo GuardrailspicklescanpromptfooWorks withAgent Development KitAG2Google AI Edge GalleryAiderany-llmAnythingLLMBAMLbrowser-useCAMELHugging Face Chat UIChatboxCherry StudioClineCodex CLICogneeCrewAIDeerFlowdocTRDSPyEasyOCREnchantedGemini CLIGitHub MCP ServergooseGPT ResearcherGradioGraphitiGuidanceHollamaInstructorKilo CodeLangflowLangGraphLiteLLMLlamaIndexLLMLocalAGILoLLMs WebUIMCP Python SDKMem0MetaGPTNextChatOllama JavaScriptOllama PythonolmOCROpenAI Agents SDKopencodeOpenHandsotermOutlinesPage AssistPlaywright MCPPortkey AI GatewayPrivateGPTQwen CodeRWKV RunnerSemantic KernelsmolagentsStrands AgentsSuryaVaneXGrammar
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

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

Original release from the publisher.

Base model: baidu/Unlimited-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 05:17 UTCpassed

Model card

From the publisher at commit 945968c. Shown as plain text with links; images open at the publisher.

Unlimited-OCR — MLX 4bit#

This repository contains the 4-bit affine quantized MLX conversion of Baidu's official baidu/Unlimited-OCR checkpoint. It is published for Apple Silicon inference with mlx-vlm and maintained for use by shuuul/aimd.

The model architecture, tokenizer, processor configuration, prompts, and MIT license come from the official checkpoint. Refer to the official model card and Unlimited-OCR repository for model details, capabilities, limitations, and attribution.

Conversion details#

SettingValue
Sourcebaidu/Unlimited-OCR
Toolmlx-vlm 0.6.8
MLX runtime used for conversionmlx 0.32.0
Output precision4bit
Quantizationaffine, group size 64
Repository size2.29 GiB

The language-model weights use uniform affine quantization with group size 64. mlx-vlm intentionally leaves unsupported or quality-sensitive multimodal modules at higher precision, so total repository size is larger than a theoretical all-layer quantization.

Conversion command:

mlx_vlm.convert \
  --hf-path baidu/Unlimited-OCR \
  --mlx-path ./Unlimited-OCR-4bit \
  --quantize --q-bits 4 --q-group-size 64 --q-mode affine

Use with AIMD#

On macOS/Apple Silicon, install AIMD and run OCR directly:

uv tool install --force "aimd-tool @ git+https://github.com/shuuul/aimd.git@main"
aimd scan.pdf --task ocr --model unlimited_ocr_4bit

unlimited_ocr defaults to the 4-bit repository. AIMD runs each page in Unlimited-OCR's single-image gundam mode with prompt document parsing., cropping=True, base_size=1024, image_size=640, and a sliding-window no-repeat n-gram guard. See the AIMD README for the complete runtime behavior.

Use with mlx-vlm#

pip install -U "mlx-vlm>=0.6.8"
python -m mlx_vlm.generate \
  --model mlx-community/Unlimited-OCR-4bit \
  --image scan.png \
  --prompt "document parsing." \
  --max-tokens 8192 \
  --temperature 0

Unlimited-OCR support first shipped in mlx-vlm 0.6.4; 0.6.8 or newer is recommended to match the conversion environment.

Available MLX weights#

PrecisionRepositorySize
4bitmlx-community/Unlimited-OCR-4bit2.29 GiB
6bitmlx-community/Unlimited-OCR-6bit2.98 GiB
8bitmlx-community/Unlimited-OCR-8bit3.66 GiB
bf16mlx-community/Unlimited-OCR-bf166.22 GiB

License and attribution#

The upstream checkpoint is released under the MIT license. This repository is a format conversion and does not modify the upstream model architecture or claim ownership of Baidu's model.

Files

15 files · 2.46 GBWeights 2.45 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md3.38 KBb77e74f5131b549262d99edac69517ff36b92b4a2cf1b4dec14c906332643a8a
chat_template.jinja191 Bb4e4771e69892ebc712ed6986bcce490c65041d1545e85599cd4a531cfab98a5
config.json3.51 KB0ecf8c737191ba53797d99359ed1cf4fb56e13ff6b80872896101cf21aa6be93
configuration_deepseek_v2.py10.7 KBb8470dd616ba8745fce6e27b093aef73a098863cc891b2477dcf9326a36000f7
conversation.py9.25 KBec7b6ce89bcda643de1f43269ffa66a7b2e65dc3ed30e427958f776546b4ba03
deepencoder.py38.0 KB0ae2fb6d1e5ae8cf100fc32f854830acd08c821a0a1f23a94a76588c222ddcf2
model.safetensors2.45 GB3797dc317a14b09c4e0ae0c324df8641c92992d60b8dab8e6318273d57c9f203
model.safetensors.index.json72.6 KBe408a502fa4df68cd92c201ca83e62522bf6545c5ba080de3c54357ea6e1680a
modeling_deepseekv2.py90.2 KB74e36e6bd0ba7bc565ef76464a99baa8e6bccb710ae9c1007b54ac30b855fa4c
modeling_unlimitedocr.py53.4 KB268bdcbe12cf37bf5a2debb53faf542e56570958a5d9f3314aab3cab2cf6cb48
processor_config.json464 Bd8972048a2a80b1921c79ef99b1e8832b013c149214b15db31bac995c9d4e935
special_tokens_map.json801 Bab4bd57ce17d62e39e0a39e739de1e407484f090f0b2c7e391312bca7a5b061a
tokenizer.json9.98 MBa02f8fd5228c90256bb4f6554c34a579d48f909e5beb232dc4afad870b55a8b4
tokenizer_config.json567 B6835b63b4534bac1094a9f4e6b136b4569772b38b81d78cc773f3aa6e6b7aa47
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
945968c0fd pinned now2026-11-15 05:17 UTC15 files · 2.46 GB

Use it

$ fw get mlx-community/Unlimited-OCR-4bit
# manifest sha256 0465d6a3267c… · 2.46 GB · 15 files
$ fw verify ./Unlimited-OCR-4bit mlx-community/Unlimited-OCR-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-4bit.json --dir ./Unlimited-OCR-4bit $ python3 fw.py verify ./Unlimited-OCR-4bit ./mlx-community__Unlimited-OCR-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Unlimited-OCR-4bit --revision 945968c0fd6883390c2ef71f26a3e9955ad379c0 --local-dir ./Unlimited-OCR-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-4bit", revision="945968c0fd6883390c2ef71f26a3e9955ad379c0") model = AutoModelForImageTextToText.from_pretrained("mlx-community/Unlimited-OCR-4bit", revision="945968c0fd6883390c2ef71f26a3e9955ad379c0", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Unlimited-OCR-4bit --revision 945968c0fd6883390c2ef71f26a3e9955ad379c0
Fine-tune in Studio

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
b77e74f5131b549262d99edac69517ff36b92b4a2cf1b4dec14c906332643a8a
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.textSubject: Unlimited-OCR-4bitDate: 2026-11-15Commit: 945968cSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Unlimited-OCR-4bit
Pinned commit
945968c0fd6883390c2ef71f26a3e9955ad379c0
Manifest
Unlimited-OCR-4bit.json · .minisig
Manifest sha256
0465d6a3267ca40087fed71d7eb921ff1036c5906a15e5c65c51f65c25bf7c98
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:17 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Unlimited-OCR-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Unlimited-OCR-4bit.json.minisig $ minisign -Vm Unlimited-OCR-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 · 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-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-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Unlimited-OCR-4bit

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