alt.freeweights.qwen / Qwen3-Embedding-4B
From: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-Embedding-4B

Date: 2026-11-14Commit: 5cf2132Signed: 2DC28CC7B26A283B ✓

Feature extraction model with 4B parameters. Safetensors weights, 8.06 GB in all. Published by Qwen under Apache-2.0.

4B params8.06GBQwen3-Embedding-4Bsafetensorspermissive
FactsParams4BSize8.06 GBFormatssafetensorsTaskfeature extractionLicenseApache-2.0From sourcepermissive
$ fw get Qwen/Qwen3-Embedding-4B
# manifest sha256 12ac11db4e37… · 8.06 GB · 14 files
$ fw verify ./Qwen3-Embedding-4B Qwen/Qwen3-Embedding-4B
From sourceQwen/Qwen3-Embedding-4BLast check: 2026-11-14 06:34 UTC

Overview

Size
8.06 GB
Weights
8.04 GB (safetensors)
Parameters
4B
Formats
safetensors
Task
feature extraction
License
Apache-2.0 (permissive)
Files
14, each with a sha256
Publisher
Qwen
Added
2026-11-14
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-4B-Base

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.co2026-11-14 06:34 UTCpassed

Files

14 files · 8.06 GBWeights 8.04 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
1_Pooling/config.json313 B0f0ed3380602b252fced3fab6d07c76752c32ffca818ccc61afaf17ae8edd96f
README.md17.3 KB3c8dafc1e6529491fa8918cd96c62b90229b317fd83f2794cea20cda100d6122
config.json727 B78d2861cbbfd80eee05839200c5a3b7ed64c789f6c1cab4fbb84cc4eae33eaf5
config_sentence_transformers.json215 B10667c72ddb772627bf1780cb7f86af8e2ae0032b8c243c731172064105c6961
generation_config.json117 B28396d421a2108acce96383f6a7de78008f7f1b17f807958f3c14c51dbfb65fb
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00002.safetensors4.97 GBe70bfe3c970523fb7ef4eddffed2254ce3f1e7150c3de2af4342de129dd756f8
model-00002-of-00002.safetensors3.08 GBed1b87c8e9eb7e535a1a155e4fd00d9f4dba80e58a6db48a4c9f82cede7079c1
model.safetensors.index.json30.4 KB9d130c7f24fa1f9a2a7e19fad42c7d6d2d6fea31b180bdf3e8aac1924c26c39a
modules.json349 B84e40c8e006c9b1d6c122e02cba9b02458120b5fb0c87b746c41e0207cf642cf
tokenizer.json11.4 MB83cdf8c3a34f68862319cb1810ee7b1e2c0a44e0864ae930194ddb76bb7feb8d
tokenizer_config.json7.26 KB2f58f4bbd7bbce15d683f525954ef3a92cd82f5e06415a9c513859bf8ab72436
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

Use it

$ fw get Qwen/Qwen3-Embedding-4B
# manifest sha256 12ac11db4e37… · 8.06 GB · 14 files
$ fw verify ./Qwen3-Embedding-4B Qwen/Qwen3-Embedding-4B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/Qwen/Qwen3-Embedding-4B.json --dir ./Qwen3-Embedding-4B $ python3 fw.py verify ./Qwen3-Embedding-4B ./Qwen__Qwen3-Embedding-4B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen3-Embedding-4B --revision 5cf2132abc99cad020ac570b19d031efec650f2b --local-dir ./Qwen3-Embedding-4B
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModel, AutoTokenizer tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-Embedding-4B", revision="5cf2132abc99cad020ac570b19d031efec650f2b") model = AutoModel.from_pretrained("Qwen/Qwen3-Embedding-4B", revision="5cf2132abc99cad020ac570b19d031efec650f2b", device_map="auto")
Run in Allternit Desktopcoming in Phase 1
Fine-tune in Freeweights Studiocoming in Phase 3

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Text in
README.md
Text sha256
3c8dafc1e6529491fa8918cd96c62b90229b317fd83f2794cea20cda100d6122
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license list. A custom license passes only after a recorded human audit.

Provenance

From: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject: Qwen3-Embedding-4BDate: 2026-11-14Commit: 5cf2132Signed: 2DC28CC7B26A283B ✓
Upstream
Qwen/Qwen3-Embedding-4B
Pinned commit
5cf2132abc99cad020ac570b19d031efec650f2b
Manifest
Qwen3-Embedding-4B.json · .minisig
Manifest sha256
12ac11db4e376a6f97173b085431cc6c877197f8a03036252be100c4e998ed6c
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:34 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3-Embedding-4B.json $ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3-Embedding-4B.json.minisig $ minisign -Vm Qwen3-Embedding-4B.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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen3-Embedding-4B
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-Embedding-4B.json. Provenance. Takedown history: none.
From: unsloth <huggingface.co/unsloth>Subject: Qwen3.8-Flash-Next-GGUF
From: XiaomiMiMo <huggingface.co/XiaomiMiMo>Subject: MiMo-V2.6-Distill-Qwen-9B
From: Qwen <huggingface.co/Qwen>Subject: Qwen-AgentWorld-35B-A3B
From: Qwen <huggingface.co/Qwen>Subject: Qwen-Image-2.1
From: Qwen <huggingface.co/Qwen>Subject: Qwen-Image-2.1-Turbo
From: Qwen <huggingface.co/Qwen>Subject: Qwen3-ASR-1.7B