CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-VL-2B-Instruct-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-VL-2B-Instruct-4bit

Date: 2026-11-15Commit: 9c4f520Signed: 2DC28CC7B26A283B ✓

Image text to text model with 2.1B parameters. Safetensors weights, 1.80 GB in all. Published by mlx-community under Apache-2.0.

2.1B params1.80GBQwen3-VL-2B-Instruct-4bitsafetensorspermissive
FactsParams2.1BSize1.80 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-VL-2B-Instruct-4bit
# manifest sha256 a497191e9fb2… · 1.80 GB · 16 files
$ fw verify ./Qwen3-VL-2B-Instruct-4bit mlx-community/Qwen3-VL-2B-Instruct-4bit
From sourceHosted (signed)mlx-community/Qwen3-VL-2B-Instruct-4bitLast check: 2026-11-15 02:47 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
1.80 GB
Weights
1.78 GB (safetensors)
Parameters
2.1B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
16, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
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 02:47 UTCpassed

Model card

From the publisher at commit 9c4f520. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-VL-2B-Instruct-4bit#

This model was converted to MLX format from Qwen/Qwen3-VL-2B-Instruct using mlx-vlm version 0.3.4. 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/Qwen3-VL-2B-Instruct-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

16 files · 1.80 GBWeights 1.78 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md599 Bede73d0babc5bc8fa1eeaed1f9564eab6e5094500e5561f94235a15c96aa1cf0
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja5.29 KB3636d0f0bd6bef02654cdffdc447b79cb2cef8ab02cc75267345946291a489e4
chat_template.json5.50 KB6f8a6a55027e3da5160105556cda5dd69f6423f1c32645f6730d32de7773d0c4
config.json7.14 KB6e992843f82cbaf02e8eae2f1c803f8a56f70951fa8a1f30fc1bf8d9ec2d7ec3
generation_config.json269 B1e241830b48b397cb0900101421df5450baddc7adf01e5fc86b5615865f3bae4
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model.safetensors1.78 GB4750d95a2162829e127a94e83ac350d498d02070aab216c4687da48804a06ffb
model.safetensors.index.json82.8 KB30ba24b1c93436450f2e202de402058ecea7417cf66785d4c73e52d1575e6d97
preprocessor_config.json782 B93585062a80db5e8ca038efc7726a3e6411d9db948472d81d63c6303993be8c5
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.45 KB81ec7bb9530159b326c0bef1d0b6c33d392090524014ea3f0123a3c1eb9c2af5
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
9c4f5209e5 pinned now2026-11-15 02:47 UTC16 files · 1.80 GB

Use it

$ fw get mlx-community/Qwen3-VL-2B-Instruct-4bit
# manifest sha256 a497191e9fb2… · 1.80 GB · 16 files
$ fw verify ./Qwen3-VL-2B-Instruct-4bit mlx-community/Qwen3-VL-2B-Instruct-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/Qwen3-VL-2B-Instruct-4bit.json --dir ./Qwen3-VL-2B-Instruct-4bit $ python3 fw.py verify ./Qwen3-VL-2B-Instruct-4bit ./mlx-community__Qwen3-VL-2B-Instruct-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-VL-2B-Instruct-4bit --revision 9c4f5209e57b31f4b9dfba735de3fb983739c9cc --local-dir ./Qwen3-VL-2B-Instruct-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/Qwen3-VL-2B-Instruct-4bit", revision="9c4f5209e57b31f4b9dfba735de3fb983739c9cc") model = AutoModelForImageTextToText.from_pretrained("mlx-community/Qwen3-VL-2B-Instruct-4bit", revision="9c4f5209e57b31f4b9dfba735de3fb983739c9cc", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-VL-2B-Instruct-4bit --revision 9c4f5209e57b31f4b9dfba735de3fb983739c9cc
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
ede73d0babc5bc8fa1eeaed1f9564eab6e5094500e5561f94235a15c96aa1cf0
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: Qwen3-VL-2B-Instruct-4bitDate: 2026-11-15Commit: 9c4f520Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-VL-2B-Instruct-4bit
Pinned commit
9c4f5209e57b31f4b9dfba735de3fb983739c9cc
Manifest
Qwen3-VL-2B-Instruct-4bit.json · .minisig
Manifest sha256
a497191e9fb28a3d4ab121faa1a3c5561b18e2ae295de3a2e3c04b5b76551a3e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:47 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-VL-2B-Instruct-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-VL-2B-Instruct-4bit.json.minisig $ minisign -Vm Qwen3-VL-2B-Instruct-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

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/Qwen3-VL-2B-Instruct-4bit
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-2B-Instruct-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-VL-2B-Instruct-4bit

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