Downloads · 30 days
28
39% of all-time downloads
FluxKlein4b-nvfp4_mixed
ApacheOne/FluxKlein4b-nvfp4_mixed
FluxKlein4b-nvfp4_mixed is a machine learning model from ApacheOne. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Pin down what is needed between 50s,40s,30s cards
All-time downloads
71
Public
Repo size
10.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors10.3 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- custom
- Access
- Public
- Created
- Feb 23, 2026
- Updated
- Mar 23, 2026
- SHA
- 0ba38b79
Base models
Model card
From the Hugging Face model README
Just some testing
Pin down what is needed between 50s,40s,30s cards
Translate info for use in TensorRT fp4 converting / onnx
Anyone that has made fp4 onnx before with NVIDIA’s Model Optimizer PTQ help in the Community tab is welcomed.
Currently working on correct Quantize/Dequantize nodes for onnx export to build fp4 RT engine for 50s cards.
Klein 4B NVFP4 Variants — txt_attn dtype notes
Klein4b-nvfp4.safetensors
txt_attnweights: NVFP4
Klein4b-nvfp4_BF16.safetensors
txt_attnweights: BF16
Klein4b-nvfp4_fp8e4m3fn_absmax.safetensors
txt_attnweights: FP8 (float8_e4m3fn)txt_attnscaling: absmax
Klein4b-nvfp4_fp8e5m2_absmax.safetensors
txt_attnweights: FP8 (float8_e5m2)txt_attnscaling: absmax
- Type
- custom
- License
- apache-2.0
- Languages
- en
- Created
- Feb 23, 2026
- Updated
- Mar 23, 2026