Downloads · 30 days
12
1% of all-time downloads
Apertus-8B-Instruct-2509-LOGEQ-FP8_dynamic
jgerster0/Apertus-8B-Instruct-2509-LOGEQ-FP8_dynamic
Apertus-8B-Instruct-2509-LOGEQ-FP8_dynamic is a machine learning model from jgerster0. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model applies Logarithmic Equalization (LogEQ) followed by full FP8 dynamic quantization using the LLM Compressor framework.
All-time downloads
1.1K
Public
Parameters
8.1B
9.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.1 GB · 100%
Parameter types
How the weights are stored.
F8_E4M37B · 87%
Base models
Model card
From the Hugging Face model README
Apertus-8B-Instruct-2509-LOGEQ-FP8_dynamic
This model applies Logarithmic Equalization (LogEQ) followed by
full FP8 dynamic quantization using the LLM Compressor framework.
What this means in practice
- LogEQ smooths and rescales activations using logarithmic statistics,
reducing activation outliers before quantization. - Both weights and activations are quantized to FP8 dynamic format
(E5M2 or E4M3 depending on layer type). - The quantized model is compatible with vLLM FP8 execution. data-free activation tracing.
Quantization Details
- Quantization Scheme: FP8_dynamic
- Preprocessing: LogarithmicEqualizationModifier
- Method: Data-free FP8 dynamic quantization
- Targets: All
Linearlayers - Ignored Layers:
lm_head(kept in FP16 for stability) - Tool: llm-compressor
- Type
- apertus
- Created
- Dec 12, 2025
- Updated
- Dec 14, 2025