FLUX 3 Image Klein
Black Forest Labs·
Overview
Open-weight 5.6B image model from the FLUX 3 family for generation, multi-reference generation and editing, with native 4K output and bounding-box control. Ships as a base model for fine-tuning and a step-distilled model for low-latency generation, in FP8, INT8 and NVFP4 builds; the INT8 build runs on GeForce RTX cards with 8 GB of VRAM through ComfyUI or Diffusers. FLUX Kommunity License: businesses under $5M annual revenue may use it commercially without a fee, larger ones need a self-hosting agreement or the API. BFL's quality claims are internal evaluations; no Arena rating yet.
Capabilities and innovations
Benchmarks
No benchmark values are recorded for this model.
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- SWE-bench Pro: not reported by the vendor
- MMLU: not reported by the vendor
- MMLU-Pro: not reported by the vendor
- Terminal-Bench 2.x: not reported by the vendor
- MMMU-Pro: not reported by the vendor
Architecture and hardware
- Parameters
- 5.6B total
- Estimated VRAM at Q4
- ~4 GB, Mobile / NPU class
Links
More from Black Forest Labs
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.