CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen-Image-2512-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen-Image-2512-8bit

Date: 2026-11-15Commit: 5f756d3Signed: 2DC28CC7B26A283B ✓

Text to image model. Safetensors weights, 36.1 GB in all. Published by mlx-community under Apache-2.0.

qwen36.1GBQwen-Image-2512-8bitsafetensorspermissive
FactsParamsnot statedSize36.1 GBFormatssafetensorsTasktext to imageLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen-Image-2512-8bit
# manifest sha256 75faf7d5385a… · 36.1 GB · 26 files
$ fw verify ./Qwen-Image-2512-8bit mlx-community/Qwen-Image-2512-8bit
From sourceHosted (signed)mlx-community/Qwen-Image-2512-8bitLast check: 2026-11-15 02:50 UTC
Run at homeGet help

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

Fine-tune of Qwen-Image.

Works with

Run16Fine-tune8Convert8Scan2
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
36.1 GB
Weights
36.1 GB (safetensors)
Parameters
not stated
Formats
safetensors
Task
text to image
License
Apache-2.0 (permissive)
Files
26, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen-Image

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 02:50 UTCpassed

Model card

From the publisher at commit 5f756d3. Shown as plain text with links; images open at the publisher.

Qwen-Image 8-bit MLX#

MLX-optimized 8-bit quantized version of Qwen-Image for Apple Silicon.

First MLX port of Qwen-Image! 🎉

Quick Start#

pip install mflux

mflux-generate-qwen \
  --model mlx-community/Qwen-Image-2512-8bit \
  --prompt "A photorealistic cat wearing a tiny top hat" \
  --steps 20

Performance#

MetricValue
Size34GB (8-bit quantized)
Speed~8.5s/step on M-series Mac
20 steps~2:50 total

Model Details#

  • Base Model: Qwen/Qwen-Image (Dec 2025)
  • Quantization: 8-bit
  • Framework: MLX (Apple Silicon optimized)
  • Converted with: mflux 0.14.0

Hardware Requirements#

  • Apple Silicon Mac (M1/M2/M3/M4/M5)
  • ~40GB unified memory recommended for 8-bit

Sample Output#

Generated with prompt: "A photorealistic cat wearing a tiny top hat, studio lighting"

All Quantizations#

License#

Apache 2.0 (same as base model)

Credits#

Files

26 files · 36.1 GBWeights 36.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 26 files with their sha256
FileSizesha256
.gitattributes1.58 KBcaf3ca02d5e883f643e939cbed54f94237f94c171797f0dfea5e25c7e33315b3
README.md1.72 KBdbaae6ae074933be7e357b23170f2be7aeb0956fce4fa21baa90fb9960ce798a
text_encoder/0.safetensors2.08 GB46e90f45429f288300aab70705cc29a20b2656c780546ce4d45c7de16b168736
text_encoder/1.safetensors2.14 GB3606b47d3d2e072dfdc6474eb38772073c1a268793f6f093915724304cbafb56
text_encoder/2.safetensors2.06 GB261117aba44f441dcb3b830aef1914fe3cba0285f53d6e643d682e0bddbcdc6f
text_encoder/3.safetensors2.14 GB1f7b2afdf8e956e1c61e5246e3e233bd60b27a3cbeb0443eb562b41984ee34e9
text_encoder/4.safetensors2.06 GB29aae859f1cbf0e72f076a3b94ce1c241d52cda9af21af46dec9ea7e4edda185
text_encoder/5.safetensors2.14 GBdff5f5e8202404364334f6cad3d5df537dbe665c96afe08bc51d99c0093d217c
text_encoder/6.safetensors1.53 GBf10ec27591a5d209a4fb188aac70c4d049e82519cf4ff5fe74ab5f8b4a765a95
text_encoder/model.safetensors.index.json24.0 KB1329e54fe24b867a276d399aa6152aabd6b56279c7e4d46a9ed638333ae3026d
tokenizer/tokenizer.json11.4 MBd2f057a8ae057412c59fd505665c848706f5d0193086f1c9a56095f72cdb403e
tokenizer/tokenizer_config.json306 B27791483516c71b34fed9baed187a595f62ba2d2338e781f31b7e9f9325e7641
transformer/0.safetensors2.15 GB6b8087a9dd0d7e2a7fec5489888ec65bc3b535b6b1e4b9c6cd6a4255a4515e11
transformer/1.safetensors2.13 GBdb7d5d35f2b3c550ca8933c30113b10cbe55b885f235adefcf3e54c1958ec929
transformer/10.safetensors381 MBa979246506d0c604f53665c983d9495cfd02fedded6c6343532e449595a3335b
transformer/2.safetensors2.11 GB07d280f7f92e534d8a017b0fc48a61bad23cb19d0d3a8fc5b137023944d169a2
transformer/3.safetensors2.13 GB0cdfdd6b1b6195821a657ef9868b994a008cc70152086848dcd51bd469edabdc
transformer/4.safetensors2.13 GB85b5a93b7736376396ba635e8238fc6c781f0016afe679d91136d88da233855c
transformer/5.safetensors2.15 GB68f60a5eac6d490c0117bf3293eb1bffff0021a65302b3e91b49bf8404c868e0
transformer/6.safetensors2.15 GB8e6fc8d844d48cd238e82e41f41451835e1cb6a02dc46287f09756f4fd74a254
transformer/7.safetensors2.15 GB2751a93241270d0d2b8ae1e337d9a40b827214894401fbb06f9f8a6757ad0dfb
transformer/8.safetensors2.15 GB1502e5ea154c1292eb2043a66be65d1a1a80ce13218ff8f17f4d53804f651444
transformer/9.safetensors2.11 GB285b48d203e35b61e9b59b93663e60e3617fa0001a022ee58b1bc80d46c40223
transformer/model.safetensors.index.json242 KB86cb3279612c37f743c89ec541b476fd798f97768c764f271af96916e6fdf983
vae/0.safetensors254 MB914d05fce775045e0ac134391c681143209ded4edf069a39e78f3fc6f4d5abbe
vae/model.safetensors.index.json13.5 KBc3bcf39f5cacdafa6caec099dd6ea1332fea0ae3306d083edb44b539674c3880
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
5f756d3e8c pinned now2026-11-15 02:50 UTC26 files · 36.1 GB

Use it

$ fw get mlx-community/Qwen-Image-2512-8bit
# manifest sha256 75faf7d5385a… · 36.1 GB · 26 files
$ fw verify ./Qwen-Image-2512-8bit mlx-community/Qwen-Image-2512-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen-Image-2512-8bit.json --dir ./Qwen-Image-2512-8bit $ python3 fw.py verify ./Qwen-Image-2512-8bit ./mlx-community__Qwen-Image-2512-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen-Image-2512-8bit --revision 5f756d3e8cc11878c6c131571d1b904202b788b7 --local-dir ./Qwen-Image-2512-8bit
Packaged for ComfyUI. Most image, video and music models run in ComfyUI . Check the publisher's page for the workflow. Freeweights does not host it.
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
dbaae6ae074933be7e357b23170f2be7aeb0956fce4fa21baa90fb9960ce798a
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: Qwen-Image-2512-8bitDate: 2026-11-15Commit: 5f756d3Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen-Image-2512-8bit
Pinned commit
5f756d3e8cc11878c6c131571d1b904202b788b7
Manifest
Qwen-Image-2512-8bit.json · .minisig
Manifest sha256
75faf7d5385a5c599f3c9b1c8d473ee3520864cba3c0fbf1e81644cbff16a339
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:50 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen-Image-2512-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen-Image-2512-8bit.json.minisig $ minisign -Vm Qwen-Image-2512-8bit.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/Qwen-Image · this model is a finetune 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/Qwen-Image-2512-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen-Image-2512-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen-Image-2512-8bit

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