---
language: en
license: apache-2.0
pipeline_tag: text-generation
tags:
  - quantization
  - nvfp4
  - swiss-ai
base_model: swiss-ai/Apertus-8B-Instruct-2509
model_name: Apertus-8B-Instruct-2509-NVFP4
---

# Apertus-8B-Instruct-2509-NVFP4

NVFP4-quantized version of `swiss-ai/Apertus-8B-Instruct-2509` produced with [llmcompressor](https://github.com/neuralmagic/llm-compressor).

## Notes
- Quantization scheme: NVFP4 (linear layers, `lm_head` excluded)
- Calibration samples: 512
- Max sequence length during calibration: 2048