Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions
FLUX 3 Image Klein
Black Forest Labs' 5.6B open-weights image model, released 15 October 2026, for text-to-image, editing and up to 10 reference images at native 4K, with builds that run on 8 GB GPUs.
TrustList summary
Not yet independently verified. Every detail here comes from Black Forest Labs' own announcement of 15 October 2026 and its Hugging Face listing; we have not yet read an independent report. The rankings in the announcement are Black Forest Labs' own evaluations, so no score is stored. We will update this when it can be confirmed, and remove this note.
FLUX 3 Image Klein is a 5.6-billion-parameter image model that Black Forest Labs released on 15 October 2026, as open weights under the FLUX Kommunity License and through the company's own API. It is the small member of the FLUX 3 family and shares the full FLUX 3 Image model's core features: native 4K generation, precise editing, and bounding boxes that place elements or confine an edit to one area.
What it does
The model handles three jobs: generating an image from a text prompt, editing an existing image, and composing a new image from up to ten reference images. Black Forest Labs says FLUX 3 draws on what it learned training across images, video and audio, so that generated scenes behave more like the real world. The release includes a base model meant for fine-tuning and a step-distilled model for low-latency generation, plus FP8, INT8 and NVFP4 builds made with NVIDIA. Diffusers and Ostris's AI Toolkit support LoRA training on the base checkpoint, and NVIDIA's NeMo AutoModel ships training recipes for it.
Who it is for
Black Forest Labs aims the model at teams that want to run or adapt an image model on their own hardware, including those with data-sovereignty or local-deployment requirements, and at on-device editing. The generator weights need 11.2 GB in BF16 and 5.6 GB in FP8; with the INT8 build the company says it runs on NVIDIA GeForce RTX cards with 8 GB of memory, producing a one-megapixel image in about four seconds on an RTX 5090 and under nine seconds on an RTX 4070 through ComfyUI, by NVIDIA's measurements. Through the BFL API the distilled model is offered as flux-3-image-klein, and the announcement says pricing "starts at $0.009 per 1K image". The announcement also ranks it first among the open models it compared in text-to-image, multi-reference generation and editing; those are the company's internal evaluations, and no score is stored here.
Key facts
Maker: Black Forest Labs Released: 15 October 2026 Size: 5.6B parameters (image generator) Tasks: text-to-image, image editing, multi-reference generation (up to 10 images) Builds: base, step-distilled; FP8, INT8, NVFP4 Licence: FLUX Kommunity License (weights on Hugging Face) API: BFL API, model flux-3-image-klein
Benchmarks & AI stats
| Benchmark | Official | Community avg |
|---|---|---|
| No benchmark scores yet. Be the first to add one. | ||
“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).
Sign in to add a benchmark score for this model.
FLUX 3 Image Klein launches
Request a demo or quote from FLUX 3 Image Klein
Reviews
Write the first review of FLUX 3 Image Klein
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about FLUX 3 Image Klein.
FLUX 3 Image Klein alternatives
Similar listings buyers compare against this one.
Black Forest Labs' image generation and editing model with bounding-box layouts, multiple reference images and 4K output
Aleph Alpha's open-weight English-German mixture-of-experts model for self-hosting, released under Apache 2.0 in October 2026
Ai2's open-weight 8B model that writes cited scientific reports from a research question and retrieved literature
Anthropic's smallest and fastest Claude 5.5 model, available on its own API and three cloud platforms
JetBrains' open 12B mixture-of-experts coding model with 2.5B parameters active per token under Apache 2.0
Perplexity's open-weight decision model that picks among given options for routing and checks in AI systems
Open-source 2B decision model from AWS's Strands Agents project that picks options and returns scores with a reliability figure
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.