CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-OCR-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-OCR-8bit

Date: 2026-11-15Commit: 0e2b0e4Signed: 2DC28CC7B26A283B ✓

Image text to text model with 3.3B parameters. Safetensors weights, 3.93 GB in all. Published by mlx-community under MIT.

3.3B params3.93GBDeepSeek-OCR-8bitsafetensorspermissive
FactsParams3.3BSize3.93 GBFormatssafetensorsTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get mlx-community/DeepSeek-OCR-8bit
# manifest sha256 a786456e1290… · 3.93 GB · 16 files
$ fw verify ./DeepSeek-OCR-8bit mlx-community/DeepSeek-OCR-8bit
From sourceHosted (signed)mlx-community/DeepSeek-OCR-8bitLast check: 2026-11-15 03:33 UTC
Run at homeGet help

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

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

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

Original release from the publisher.

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 03:33 UTCpassed

Model card

From the publisher at commit 0e2b0e4. Shown as plain text with links; images open at the publisher.

mlx-community/DeepSeek-OCR-8bit#

This model was converted to MLX format from prince-canuma/DeepSeek-OCR using mlx-vlm version 0.3.10. 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/DeepSeek-OCR-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

16 files · 3.93 GBWeights 3.92 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md653 B102ef25cc8af02639d741d82cccf6c3b26b2d8e4f1846e494a1acc7c74b9406e
chat_template.jinja191 Bb4e4771e69892ebc712ed6986bcce490c65041d1545e85599cd4a531cfab98a5
chat_template.json217 B9aec9391d364b0da5bdee6af557e3d76b3e2ae999610888186df2679f7b27ef7
config.json3.40 KB0cab2fa0ea343a83eee80ad801f7adfa3bbf9a0e771a4425d2592eff473ed409
configuration_deepseek_v2.py10.6 KB6ab21f29a4722e26fa28c8e0d4277591689a598df17cf6c712330e8f62b3fc7c
conversation.py9.25 KBec7b6ce89bcda643de1f43269ffa66a7b2e65dc3ed30e427958f776546b4ba03
deepencoder.py38.0 KB0ae2fb6d1e5ae8cf100fc32f854830acd08c821a0a1f23a94a76588c222ddcf2
model.safetensors3.92 GBfb3cf7b019cedc21ab22ac08fd9e83d4fffa92d3581d73b47e6d0ee5bf308aa0
model.safetensors.index.json72.6 KB276274f47b11187d0d65a45c31d38786808b4b4332e5062b001eb8243a5fc1f0
modeling_deepseekocr.py40.1 KB5835e0b9e1942fe36df9123009d1d80a2b78ccbe6a2d535668a6561e3d4068b1
modeling_deepseekv2.py82.2 KB69184a0493d1fdac21c360f9f9eabc5b5af3188e0265df44cfaeafc44f9095e3
processor_config.json460 B0fe7ba9aa6b967a90e4af40d43c8030cbdd3dbcfbb387b8907625d5e54f0dbbe
special_tokens_map.json801 Bab4bd57ce17d62e39e0a39e739de1e407484f090f0b2c7e391312bca7a5b061a
tokenizer.json9.98 MBa02f8fd5228c90256bb4f6554c34a579d48f909e5beb232dc4afad870b55a8b4
tokenizer_config.json577 Bfe8b80f22dd322ca2c50a2ed97daabdbf4a672cd21ff90bf4a9851574bb3f9d4
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0e2b0e4922 pinned now2026-11-15 03:33 UTC16 files · 3.93 GB

Use it

$ fw get mlx-community/DeepSeek-OCR-8bit
# manifest sha256 a786456e1290… · 3.93 GB · 16 files
$ fw verify ./DeepSeek-OCR-8bit mlx-community/DeepSeek-OCR-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/DeepSeek-OCR-8bit.json --dir ./DeepSeek-OCR-8bit $ python3 fw.py verify ./DeepSeek-OCR-8bit ./mlx-community__DeepSeek-OCR-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-OCR-8bit --revision 0e2b0e49226b5d9efc4799f4c5b1a5f423a90178 --local-dir ./DeepSeek-OCR-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/DeepSeek-OCR-8bit", revision="0e2b0e49226b5d9efc4799f4c5b1a5f423a90178") model = AutoModelForImageTextToText.from_pretrained("mlx-community/DeepSeek-OCR-8bit", revision="0e2b0e49226b5d9efc4799f4c5b1a5f423a90178", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/DeepSeek-OCR-8bit --revision 0e2b0e49226b5d9efc4799f4c5b1a5f423a90178
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
102ef25cc8af02639d741d82cccf6c3b26b2d8e4f1846e494a1acc7c74b9406e
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.deepseekSubject: DeepSeek-OCR-8bitDate: 2026-11-15Commit: 0e2b0e4Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/DeepSeek-OCR-8bit
Pinned commit
0e2b0e49226b5d9efc4799f4c5b1a5f423a90178
Manifest
DeepSeek-OCR-8bit.json · .minisig
Manifest sha256
a786456e1290b630c46124c8526ef25363cf43211363c2ed7b9001bb1fb09514
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:33 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-OCR-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-OCR-8bit.json.minisig $ minisign -Vm DeepSeek-OCR-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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-OCR-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-OCR-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/DeepSeek-OCR-8bit

Related models

All of alt.freeweights.deepseek →
From: timm <huggingface.co/timm>Subject: deepseek_vit_412m.deepseek_v4_1_flash
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-R1-0528-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-V3-0324-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-V3.1-GGUF
From: mlx-community <huggingface.co/mlx-community>Subject: deepseek-ai-DeepSeek-V4-Flash-8bit