CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.5-2B-MLX-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-2B-MLX-4bit

Date: 2026-11-14Commit: 93760beSigned: 2DC28CC7B26A283B ✓

Model with 2.2B parameters. Safetensors weights, 1.75 GB in all. Published by mlx-community under Apache-2.0.

2.2B params1.75GBQwen3.5-2B-MLX-4bitsafetensorspermissive
FactsParams2.2BSize1.75 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3.5-2B-MLX-4bit
# manifest sha256 acbd2a321dc6… · 1.75 GB · 12 files
$ fw verify ./Qwen3.5-2B-MLX-4bit mlx-community/Qwen3.5-2B-MLX-4bit
From sourceHosted (signed)mlx-community/Qwen3.5-2B-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 Qwen3.5-2B.

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
1.75 GB
Weights
1.72 GB (safetensors)
Parameters
2.2B
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/Qwen3.5-2B

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 93760be. Shown as plain text with links; images open at the publisher.

Qwen3.5-2B-MLX-4bit#

This is a 4-bit quantized MLX version of Qwen/Qwen3.5-2B for Apple Silicon.

Model Details#

  • Original Model: Qwen/Qwen3.5-2B
  • Quantization: 4-bit (6.225 bits per weight)
  • Group Size: 64
  • Format: MLX SafeTensors
  • Framework: mlx-vlm
  • Disk Size: ~1.6G

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/Qwen3.5-2B" \
  --mlx-path "./Qwen3.5-2B-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/Qwen3.5-2B-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/Qwen3.5-2B-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 · 1.75 GBWeights 1.72 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.27 KB34decba3365c0f0e712aec28f0e49f82283bc22dc26174131ffee5279012b23c
chat_template.jinja7.75 KB273d8e0e683b885071fb17e08d71e5f2a5ddfb5309756181681de4f5a1822d80
config.json3.11 KBbeb7fc5a6e0405fe332821cf1a8ef7b69bb390a8c8933171647de5579debf949
model.safetensors1.72 GB713fe7e5d3c3965f7106b0d0ee17615f7869c23c8d327996df8c1196fbcf07d5
model.safetensors.index.json81.7 KB8294c05cca7d53a6c33e3db2b379539bd296d054e0b689711b16b6ac93c7e49d
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
93760be4f1 pinned now manifest updated, same commit2026-11-14 21:30 UTC12 files · 1.75 GB
93760be4f12026-11-14 21:30 UTC12 files · 1.75 GB

Use it

$ fw get mlx-community/Qwen3.5-2B-MLX-4bit
# manifest sha256 acbd2a321dc6… · 1.75 GB · 12 files
$ fw verify ./Qwen3.5-2B-MLX-4bit mlx-community/Qwen3.5-2B-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/Qwen3.5-2B-MLX-4bit.json --dir ./Qwen3.5-2B-MLX-4bit $ python3 fw.py verify ./Qwen3.5-2B-MLX-4bit ./mlx-community__Qwen3.5-2B-MLX-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.5-2B-MLX-4bit --revision 93760be4f1f69842a46bc13dbdc0f19e291392a3 --local-dir ./Qwen3.5-2B-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
34decba3365c0f0e712aec28f0e49f82283bc22dc26174131ffee5279012b23c
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: Qwen3.5-2B-MLX-4bitDate: 2026-11-14Commit: 93760beSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3.5-2B-MLX-4bit
Pinned commit
93760be4f1f69842a46bc13dbdc0f19e291392a3
Manifest
Qwen3.5-2B-MLX-4bit.json · .minisig
Manifest sha256
acbd2a321dc6f188ca925cca7e6604fc4dac339fe0d7034005d9eeb9e6b00e18
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/Qwen3.5-2B-MLX-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-2B-MLX-4bit.json.minisig $ minisign -Vm Qwen3.5-2B-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/Qwen3.5-2B · 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/Qwen3.5-2B-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. Qwen3.5-2B-MLX-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3.5-2B-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