audenvenn/h3metal-flux2-klein-4b
text-to-image model by audenvenn
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[FLUX.2 [klein] 4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-4B) by Black Forest Labs, converted for h3metal, an open-source (Apache-2.0) inference engine for Apple silicon that runs the model on the matrix units of M5- and M6-class GPUs. These files are h3metal's own format: they do not load in diffusers or other libraries. It needs h3metal 0.5.1 or later, a Mac with an M5- or M6-class GPU, macOS 26 and Python 3.10 or later. At 1024 x 1024 h3metal uses about 7 GB of memory: the transformer's 4.5 GB file, which it maps instead of copying, and 2.2 GB besides. LoRA adapters for FLUX.2 [klein] 4B work with these files (--lora FILE[:STRENGTH]), in diffusers', kohya's or the original checkpoint's layout; h3metal applies them exactly, as low-rank terms inside its int8 products (docs/lora.md). On a Mac mini (M6, 24 GB), a 1024 x 1024 image takes 7.4 s from a new prompt (four steps, the whole run from…
Read the full model card ↗ · Preview checked 2026-11-13T07:19:58.804Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
audenvenn/h3metal-flux2-klein-4b is a text-to-image model repository published by audenvenn on Hugging Face. The source reports the h3metal library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-image
- Library
- h3metal
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-13T06:32:50.000Z
- Last modified
- 2026-11-13T06:49:44.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: black-forest-labs/FLUX.2-klein-4B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-13T06:57:58.356Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
stabilityai/stable-diffusion-xl-base-1.0
abenzerps/Qwen-Image-2.1-Uncensored-Quantized