CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-VL-4B-Thinking-MLX-6bit
From: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-VL-4B-Thinking-MLX-6bit

Date: 2026-11-15Commit: 3c48f7eSigned: 2DC28CC7B26A283B ✓

Image text to text model with 4.4B parameters. Safetensors weights, 4.12 GB in all. Published by lmstudio-community under Apache-2.0.

4.4B params4.12GBQwen3-VL-4B-Thinking-MLX-6bitsafetensorspermissive
FactsParams4.4BSize4.12 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit
# manifest sha256 841da6c73e87… · 4.12 GB · 16 files
$ fw verify ./Qwen3-VL-4B-Thinking-MLX-6bit lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit
From sourceHosted (signed)lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bitLast check: 2026-11-15 05:24 UTC
Run at homeGet help

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

Quantized of Qwen3-VL-4B-Thinking.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
4.12 GB
Weights
4.10 GB (safetensors)
Parameters
4.4B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
16, each with a sha256
Publisher
lmstudio-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-VL-4B-Thinking

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 05:24 UTCpassed

Model card

From the publisher at commit 3c48f7e. Shown as plain text with links; images open at the publisher.

💫 Community Model> Qwen3-VL-4B-Thinking by Qwen#

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.

Model creator: Qwen

Original model: Qwen3-VL-4B-Thinking

MLX quantization: provided by LM Studio team using mlx_vlm

LM Studio model page: Qwen3-VL

Technical Details#

6-bit quantized version of Qwen3-VL-4B-Thinking using MLX, optimized for Apple Silicon.

Special thanks#

🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.

Disclaimers#

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Files

16 files · 4.12 GBWeights 4.10 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.28 KBa6fc56a6be592046d1548577ede559e1d3bc837e0629626346440530f8445792
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja5.20 KB36e042fe45641f067b1f2381fcc8955d10d956a3ed333ecdf7f7eb0916f68956
chat_template.json5.41 KB7dc0b863a3cf9320e063574e0adb1382a22a089f1eeb8bfbe33cc69c5c2cc1e5
config.json7.14 KBe4a0d74d482c70f606e2557dbe23eaa6e394fa8a3519606d74ecc14472319478
generation_config.json270 Bfe72e86576da6dc6886b1083d9216296dcfa085e7a86feb3c8888a1faa52e656
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model.safetensors4.10 GB0045b436ef083b5d037119175c05d6e9d90b15197ad64c232632db7c9dc8f7d1
model.safetensors.index.json64.7 KB58a7841d7bff2548dd91577d216274a83cf1b500bc6a534b809d6c1b1707cf2b
preprocessor_config.json782 B93585062a80db5e8ca038efc7726a3e6411d9db948472d81d63c6303993be8c5
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json10.9 KB1c6170b5e6797141d2a8e618f18097a8934f1706d6139f20ffaa1a4ce1953b53
video_preprocessor_config.json817 B59c5c9eb52182eb14c06ffb10ca9effd29adce5f238a95de23ca14a38dbd2cb1
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
3c48f7ebc2 pinned now2026-11-15 05:24 UTC16 files · 4.12 GB

Use it

$ fw get lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit
# manifest sha256 841da6c73e87… · 4.12 GB · 16 files
$ fw verify ./Qwen3-VL-4B-Thinking-MLX-6bit lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit.json --dir ./Qwen3-VL-4B-Thinking-MLX-6bit $ python3 fw.py verify ./Qwen3-VL-4B-Thinking-MLX-6bit ./lmstudio-community__Qwen3-VL-4B-Thinking-MLX-6bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit --revision 3c48f7ebc2275f409bcf439f0cbaf062417484ab --local-dir ./Qwen3-VL-4B-Thinking-MLX-6bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit", revision="3c48f7ebc2275f409bcf439f0cbaf062417484ab") model = AutoModelForImageTextToText.from_pretrained("lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit", revision="3c48f7ebc2275f409bcf439f0cbaf062417484ab", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit --revision 3c48f7ebc2275f409bcf439f0cbaf062417484ab
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. 2026-11-15
Text in
README.md
Text sha256
a6fc56a6be592046d1548577ede559e1d3bc837e0629626346440530f8445792
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: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.qwenSubject: Qwen3-VL-4B-Thinking-MLX-6bitDate: 2026-11-15Commit: 3c48f7eSigned: 2DC28CC7B26A283B ✓
Upstream
lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit
Pinned commit
3c48f7ebc2275f409bcf439f0cbaf062417484ab
Manifest
Qwen3-VL-4B-Thinking-MLX-6bit.json · .minisig
Manifest sha256
841da6c73e8708851d872b097732ab58f3bc7ec9ba232eb11b9e90e9acbc5780
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:24 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit.json $ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit.json.minisig $ minisign -Vm Qwen3-VL-4B-Thinking-MLX-6bit.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/Qwen3-VL-4B-Thinking · 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 lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-VL-4B-Thinking-MLX-6bit.json. Provenance. Takedown history: none.
Source
huggingface.co/lmstudio-community/Qwen3-VL-4B-Thinking-MLX-6bit

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