Downloads · 30 days
58
44% of all-time downloads
Apertus-v1.5-8B-text-4bit
TyKaoz/Apertus-v1.5-8B-text-4bit
Apertus-v1.5-8B-text-4bit is a text generation model from TyKaoz. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
4-bit MLX quantization of swiss-ai/Apertus-v1.5-8B, for Apple Silicon (~4.2 GB). Text branch of the omni checkpoint (the image and audio towers and codebooks are not included), extracted from the original weights and…
All-time downloads
132
Public
Parameters
8.1B
4.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.5 GB · 100%
Parameter types
How the weights are stored.
U328.1B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Apertus v1.5 8B text — 4-bit MLX
4-bit MLX quantization of
swiss-ai/Apertus-v1.5-8B, for Apple Silicon (~4.2 GB).
Text branch of the omni checkpoint (the image and audio towers and codebooks are not included), extracted from the original weights and quantized with mlx-lm. xIELU activation, 262144-token context, the source tokenizer and chat template. Apertus is the fully open model of the Swiss AI Initiative (EPFL, ETH Zurich, CSCS).
Usage
pip install -U mlx-lm
mlx_lm.generate \
--model TyKaoz/Apertus-v1.5-8B-text-4bit \
--prompt "Explique la quantization en une phrase." \
--max-tokens 200
| Base | Tool | Precision | Size |
|---|---|---|---|
swiss-ai/Apertus-v1.5-8B | mlx-lm | 4-bit · group 64 | ~4.2 GB |
By TyKaoz — privacy-first native macOS LLM chat client. Apache 2.0, inherited from the base model, with the Apertus acceptable use policy.
- Task
- Text Generation
- Library
- mlx
- Type
- apertus
- License
- apache-2.0
- Languages
- en, fr, de, it, rm
- Created
- Sep 18, 2026
- Updated
- Sep 18, 2026