alt.freeweights.image / FLUX.2-Klein-4B-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.imageSubject:

FLUX.2-Klein-4B-4bit

Date: 2026-11-15Commit: 1cebb9bSigned: 2DC28CC7B26A283B ✓

Image to image model. Safetensors weights, 4.62 GB in all. Published by mlx-community under Apache-2.0.

image4.62GBFLUX.2-Klein-4B-4bitsafetensorspermissive
FactsParamsnot statedSize4.62 GBFormatssafetensorsTaskimage to imageLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/FLUX.2-Klein-4B-4bit
# manifest sha256 18fb04a11124… · 4.62 GB · 14 files
$ fw verify ./FLUX.2-Klein-4B-4bit mlx-community/FLUX.2-Klein-4B-4bit
From sourceHosted (signed)mlx-community/FLUX.2-Klein-4B-4bitLast check: 2026-11-15 02:39 UTC

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

Fine-tune of FLUX.2-klein-4B.

Works with

Overview

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

Original release from the publisher.

Base model: black-forest-labs/FLUX.2-klein-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.co2026-11-15 02:39 UTCpassed

Model card

From the publisher at commit 1cebb9b. Shown as plain text with links; images open at the publisher.

This model is 4-bit quantized and the original model at https://huggingface.co/black-forest-labs/FLUX.2-klein-4B

The FLUX.2 [klein] model family are our fastest image models to date. FLUX.2 [klein] unifies generation and editing in a single compact architecture, delivering state-of-the-art quality with end-to-end inference in as low as under a second. Built for applications that require real-time image generation without sacrificing quality, and runs on consumer hardware, with as little as 13GB VRAM.

FLUX.2 [klein] 4B is a 4 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.

Fully open under Apache 2.0. Our most accessible model runs on consumer GPUs like the RTX 3090/4070. Compact but capable: supports text-to-image, image editing, and multi-reference at quality that punches above its size. Built for local development, edge deployment, and production use.

Files

14 files · 4.62 GBWeights 4.61 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.DS_Store6.15 KBddc95a1f90ce49b0160a64d5b7afe17f403071006e16df53e7de133507e10fa5
.gitattributes1.58 KBcaf3ca02d5e883f643e939cbed54f94237f94c171797f0dfea5e25c7e33315b3
README.md1.17 KB995c7463797804885f8d53321fb312a86f95a85175a13c7789940af2f115ebfa
text_encoder/0.safetensors2.14 GB4e6e8808772e8d2451fb956521d11150521e2dbe26387512c906ec7cca5543af
text_encoder/1.safetensors128 MBb4290e224bfc0aedce3ff3f500e1dcbf9b7ec6232e755daa1b469d92accaf1f2
text_encoder/model.safetensors.index.json51.3 KB373e85c5349d9575dd52d84e881c8031b07880ac8a34ba20ecddc78ac87248b7
tokenizer/chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
tokenizer/tokenizer.json11.4 MBbe75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer/tokenizer_config.json376 B779410a34a98fb2c6c925a1be6f24d632f1723473161b037f6676eb6c04886c6
transformer/0.safetensors2.15 GB0834a7f4c1c933b1abbdbad67ece489b60f308d478ffd2c14c73950bb2a43a54
transformer/1.safetensors34.7 MBcc06d157e656857a47d429b1869314ccb136b986d43d92792674c3319f6ea560
transformer/model.safetensors.index.json26.9 KB9385ea2b8d473fdbb6fdff8d1e6678466d65815ed517c00da396a81e45997cc7
vae/0.safetensors165 MB8e83c0cd6c9f697a5966f198ab59470f9db51906ae82adae314f3580792d1cb1
vae/model.safetensors.index.json17.5 KBf1b4b3083865554d05cea71b422037db40ed646fd724060fcee6d94362c56e37
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1cebb9b45c pinned now2026-11-15 02:39 UTC14 files · 4.62 GB

Use it

$ fw get mlx-community/FLUX.2-Klein-4B-4bit
# manifest sha256 18fb04a11124… · 4.62 GB · 14 files
$ fw verify ./FLUX.2-Klein-4B-4bit mlx-community/FLUX.2-Klein-4B-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/FLUX.2-Klein-4B-4bit.json --dir ./FLUX.2-Klein-4B-4bit $ python3 fw.py verify ./FLUX.2-Klein-4B-4bit ./mlx-community__FLUX.2-Klein-4B-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/FLUX.2-Klein-4B-4bit --revision 1cebb9b45c21ece14a42615b16bf5fa4de9b56da --local-dir ./FLUX.2-Klein-4B-4bit
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.

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
995c7463797804885f8d53321fb312a86f95a85175a13c7789940af2f115ebfa
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.imageSubject: FLUX.2-Klein-4B-4bitDate: 2026-11-15Commit: 1cebb9bSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/FLUX.2-Klein-4B-4bit
Pinned commit
1cebb9b45c21ece14a42615b16bf5fa4de9b56da
Manifest
FLUX.2-Klein-4B-4bit.json · .minisig
Manifest sha256
18fb04a111248fc1871a342e53f99fa1b3228d0933aa5c75cca9afebf89507b1
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:39 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/FLUX.2-Klein-4B-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/FLUX.2-Klein-4B-4bit.json.minisig $ minisign -Vm FLUX.2-Klein-4B-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

black-forest-labs/FLUX.2-klein-4B · 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/FLUX.2-Klein-4B-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. FLUX.2-Klein-4B-4bit.json. Provenance. Takedown history: none.
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: Boogu-Image
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: Chroma1-HD
From: lodestones <huggingface.co/lodestones>Subject: Chroma1-HD
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: Chroma1-Radiance
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: ERNIE-Image
From: baidu <huggingface.co/baidu>Subject: ERNIE-Image