CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.5-4B-MLX-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-4B-MLX-4bit

Date: 2026-11-14Commit: 32f3e8eSigned: 2DC28CC7B26A283B ✓

Model with 4.5B parameters. Safetensors weights, 3.06 GB in all. Published by mlx-community under Apache-2.0.

4.5B params3.06GBQwen3.5-4B-MLX-4bitsafetensorspermissive
FactsParams4.5BSize3.06 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3.5-4B-MLX-4bit
# manifest sha256 5539edc8f50f… · 3.06 GB · 12 files
$ fw verify ./Qwen3.5-4B-MLX-4bit mlx-community/Qwen3.5-4B-MLX-4bit
From sourceHosted (signed)mlx-community/Qwen3.5-4B-MLX-4bitLast check: 2026-11-14 21:30 UTC
Run at homeGet help

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

Quantized of Qwen3.5-4B.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
3.06 GB
Weights
3.03 GB (safetensors)
Parameters
4.5B
Formats
safetensors
Task
not tagged
License
Apache-2.0 (permissive)
Files
12, each with a sha256
Publisher
mlx-community
Added
2026-11-14
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.5-4B

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 21:30 UTCpassed

Model card

From the publisher at commit 32f3e8e. Shown as plain text with links; images open at the publisher.

Qwen3.5-4B-MLX-4bit#

This is a 4-bit quantized MLX version of Qwen/Qwen3.5-4B for Apple Silicon.

Model Details#

  • Original Model: Qwen/Qwen3.5-4B
  • Quantization: 4-bit (5.347 bits per weight)
  • Group Size: 64
  • Format: MLX SafeTensors
  • Framework: mlx-vlm
  • Disk Size: ~2.9G

Conversion Details#

This model was converted using mlx-vlm from the pc/fix-qwen35-predicate branch, which includes fixes for Qwen3.5 model support (proper handling of MoE gate layers, shared_expert_gate, and A_log casting).

Conversion command:

python3 -m mlx_vlm convert \
  --hf-path "Qwen/Qwen3.5-4B" \
  --mlx-path "./Qwen3.5-4B-MLX-4bit" \
  -q --q-bits 4 --q-group-size 64

Important Note#

A better, more optimized conversion may be available from @Prince (@Blaizzy) in the MLX VLM community. Check the mlx-community organization for updated versions as official Qwen3.5 support is merged into the main mlx-vlm branch.

Usage#

from mlx_vlm import load, generate

model, processor = load("mlx-community/Qwen3.5-4B-MLX-4bit")

output = generate(
    model,
    processor,
    prompt="Describe this image.",
    image="path/to/image.jpg",
    max_tokens=512
)
print(output)

CLI:

python3 -m mlx_vlm.generate \
  --model mlx-community/Qwen3.5-4B-MLX-4bit \
  --image path/to/image.jpg \
  --prompt "Describe this image."

License#

This model inherits the Apache 2.0 license from the original Qwen model.

Files

12 files · 3.06 GBWeights 3.03 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.27 KB49c0a725bdd22705d2d34b93cfe20463b673e3339ce4de8b81a340c05cfef5bc
chat_template.jinja7.76 KBa4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715
config.json3.37 KBf3efc81b2ea8d96a45301037d3ccccbcccdef44a961845c87f286aaddbc6eaaa
model.safetensors3.03 GB5fb9acd0246866381cf8c5c354c6db1019f6498eec4ccb4f5edcc71ffeacb2db
model.safetensors.index.json102 KB52e534c41f7b97708329c85f762e5882bf48bd5955a422c6ae74eba321e6048a
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
processor_config.json1.30 KB14932921ca485d458a04dafd8069fbb0a4505622a48208d19ed247115801385b
tokenizer.json20.0 MB87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
tokenizer_config.json1.14 KBe98f1901ac6f0adff67b1d540bfa0c36ac1a0cf59eb72ed78146ef89aafa1182
video_preprocessor_config.json385 B7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
32f3e8ecf6 pinned now manifest updated, same commit2026-11-14 21:30 UTC12 files · 3.06 GB
32f3e8ecf62026-11-14 21:30 UTC12 files · 3.06 GB

Use it

$ fw get mlx-community/Qwen3.5-4B-MLX-4bit
# manifest sha256 5539edc8f50f… · 3.06 GB · 12 files
$ fw verify ./Qwen3.5-4B-MLX-4bit mlx-community/Qwen3.5-4B-MLX-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/Qwen3.5-4B-MLX-4bit.json --dir ./Qwen3.5-4B-MLX-4bit $ python3 fw.py verify ./Qwen3.5-4B-MLX-4bit ./mlx-community__Qwen3.5-4B-MLX-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.5-4B-MLX-4bit --revision 32f3e8ecf65426fc3306969496342d504bfa13f3 --local-dir ./Qwen3.5-4B-MLX-4bit
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. 2026-11-14
Text in
README.md
Text sha256
49c0a725bdd22705d2d34b93cfe20463b673e3339ce4de8b81a340c05cfef5bc
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: Qwen3.5-4B-MLX-4bitDate: 2026-11-14Commit: 32f3e8eSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3.5-4B-MLX-4bit
Pinned commit
32f3e8ecf65426fc3306969496342d504bfa13f3
Manifest
Qwen3.5-4B-MLX-4bit.json · .minisig
Manifest sha256
5539edc8f50f67994d7cbaee901d9be4c179a3f6a04595a3a256dfdfe2d9f01d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:30 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-4B-MLX-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-4B-MLX-4bit.json.minisig $ minisign -Vm Qwen3.5-4B-MLX-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

Parent

Qwen/Qwen3.5-4B · 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 mlx-community/Qwen3.5-4B-MLX-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.5-4B-MLX-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3.5-4B-MLX-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