Apertus-8B-Instruct-2509-NVFP4
NVFP4-quantized version of swiss-ai/Apertus-8B-Instruct-2509 produced with llmcompressor.
Notes
- Quantization scheme: NVFP4 (linear layers,
lm_headexcluded) - Calibration samples: 512
- Max sequence length during calibration: 2048
- Downloads last month
- 186
Model tree for llmat/Apertus-8B-Instruct-2509-NVFP4
Base model
swiss-ai/Apertus-8B-2509
Finetuned
swiss-ai/Apertus-8B-Instruct-2509