alt.freeweights.qwen / Qwen3.5-4B-Base
From: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-4B-Base

Date: 2026-11-14Commit: 1001bb4Signed: 2DC28CC7B26A283B ✓

Image text to text model with 4.7B parameters. Safetensors weights, 9.34 GB in all. Published by Qwen under Apache-2.0.

4.7B params9.34GBQwen3.5-4B-Basesafetensorspermissive
FactsParams4.7BSize9.34 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get Qwen/Qwen3.5-4B-Base
# manifest sha256 7979ea2c5b98… · 9.34 GB · 13 files
$ fw verify ./Qwen3.5-4B-Base Qwen/Qwen3.5-4B-Base
From sourceQwen/Qwen3.5-4B-BaseLast check: 2026-11-14 06:33 UTC
Runs withvLLMSGLangFine-tune withAxolotlTRLPEFTUnsloth

Overview

Size
9.34 GB
Weights
9.32 GB (safetensors)
Parameters
4.7B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
13, each with a sha256
Publisher
Qwen
Added
2026-11-14
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.co2026-11-14 06:33 UTCpassed

Files

13 files · 9.34 GBWeights 9.32 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 13 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE11.3 KB50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
README.md3.72 KB76ead24ea3de5a52610c755ffa0b6e7cb51e3c413f124a3776bc6f16b694474e
config.json3.16 KBddc63e1c717afa86c865bb5e01313d89d72bb53b97ad4a8a03ba8510c0621670
merges.txt3.35 MBa9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
model.safetensors-00001-of-00002.safetensors5.33 GBdf547074dce70532a0493e5433152bd17a65efb89088cfabc2e7e2371a93d712
model.safetensors-00002-of-00002.safetensors3.99 GB590fbaac095dd31db886c322d9d2f7df47777966391acf306ddddc3e4e3a15ef
model.safetensors.index.json76.2 KBeae340074abb0a5f31a6621f7ae8e8248a7c1790df04a722c4e4b70c2a6d1dbb
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
tokenizer.json12.8 MBfe000e3ed39ed12b8d2481d527d44f93c65d37e87645d2dcc80d1bf9d50d2927
tokenizer_config.json16.7 KB3891e840d7dc5fca0af33d3a25083a735e36fe06214e3f707024820cb6b9f89c
video_preprocessor_config.json386 Bd039cd7d88b3502a99edd455496b75b44ecf7dd3b3669748bafac37e6cecc085
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003

Use it

$ fw get Qwen/Qwen3.5-4B-Base
# manifest sha256 7979ea2c5b98… · 9.34 GB · 13 files
$ fw verify ./Qwen3.5-4B-Base Qwen/Qwen3.5-4B-Base
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-4B-Base.json --dir ./Qwen3.5-4B-Base $ python3 fw.py verify ./Qwen3.5-4B-Base ./Qwen__Qwen3.5-4B-Base.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen3.5-4B-Base --revision 1001bb4d826a52d1f399e183466143f4da7b741b --local-dir ./Qwen3.5-4B-Base
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("Qwen/Qwen3.5-4B-Base", revision="1001bb4d826a52d1f399e183466143f4da7b741b") model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3.5-4B-Base", revision="1001bb4d826a52d1f399e183466143f4da7b741b", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve Qwen/Qwen3.5-4B-Base --revision 1001bb4d826a52d1f399e183466143f4da7b741b
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
LICENSE
Text sha256
50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
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: Qwen3.5-4B-BaseDate: 2026-11-14Commit: 1001bb4Signed: 2DC28CC7B26A283B ✓
Upstream
Qwen/Qwen3.5-4B-Base
Pinned commit
1001bb4d826a52d1f399e183466143f4da7b741b
Manifest
Qwen3.5-4B-Base.json · .minisig
Manifest sha256
7979ea2c5b98ab3d942499b1e32d2d5e75174fa2343c9d5b7390208241cc6676
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:33 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-4B-Base.json $ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-4B-Base.json.minisig $ minisign -Vm Qwen3.5-4B-Base.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/Qwen3.5-4B-Base
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.5-4B-Base.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