Downloads · 30 days
7
8% of all-time downloads
FLUX2-TE-Trimmed7L-Research
WaveCut/FLUX2-TE-Trimmed7L-Research
FLUX2-TE-Trimmed7L-Research is a machine learning model from WaveCut. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
WARNING: Experimental research artifact. Do NOT use in production.
All-time downloads
91
Public
Parameters
5.7B
11.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors11.3 GB · 100%
At a glance
- Model type
- mistral3
- Access
- Public
- Created
- Nov 27, 2025
- Updated
- Nov 27, 2025
- SHA
- 98734754
Model card
From the Hugging Face model README
FLUX2-TE-Trimmed7L-Research
WARNING: Experimental research artifact. Do NOT use in production.
What this is
- Model name: FLUX2-TE-Trimmed7L-Research
- Text transformer depth: 7 layers
- Vision tower depth: 24 layers (unchanged)
Caveats
- Intended for experimentation and further distillation, not end-user deployment.
- Rotary and patch positional inv_freq buffers are created at load time (not stored).
How it was built
- Shrank teacher text path to 7 layers (evenly spaced) while keeping vision depth intact.
- Stream-copied only needed tensors; other text layers were pruned.
- Type
- mistral3
- Created
- Nov 27, 2025
- Updated
- Nov 27, 2025