Downloads · 30 days
8
0% of all-time downloads
Apertus-8B-Instruct-2509-W8A16
jgerster0/Apertus-8B-Instruct-2509-W8A16
Apertus-8B-Instruct-2509-W8A16 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 is an INT8 weight-only quantized version of swiss-ai/Apertus-8B-Instruct-2509 using llm-compressor.
All-time downloads
2.2K
Public
Parameters
2.8B
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.
I327B · 87%
Model card
From the Hugging Face model README
Apertus-8B-Instruct-2509-W8A16
This is an INT8 weight-only quantized version of swiss-ai/Apertus-8B-Instruct-2509 using llm-compressor.
💡 What this means in practice
- Only the weights are quantized to 8-bit integers (INT8)
- Activations remain FP16/BF16
- No FP8 is used in this configuration
- Faster inference, reduced memory, minimal accuracy loss
Quantization Details
- Quantization Scheme: W8A16 (INT8 weights, FP16 activations)
- Method: Weight-only INT8 quantization
- Targets: All
Linearlayers - Ignored Layers:
lm_head(kept in higher precision) - Tool: llm-compressor
- Type
- apertus
- Created
- Dec 9, 2025
- Updated
- Dec 18, 2025