Downloads · 30 days
38
20% of all-time downloads
IRF-QWEN8B-mlx-Q4
FritzStack/IRF-QWEN8B-mlx-Q4
IRF-QWEN8B-mlx-Q4 is a text generation model from FritzStack. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
The Model FritzStack/IRF-Qwen8B4bit-merged2epo-mlx-4Bit was converted to MLX format from FritzStack/IRF-Qwen8B4bit-merged2epo using mlx-lm version 0.29.1.
All-time downloads
189
Public
Parameters
8.2B
4.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.6 GB · 100%
Parameter types
How the weights are stored.
U328.2B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
FritzStack/IRF-Qwen_8B_4bit-merged_2epo-mlx-4Bit
The Model FritzStack/IRF-Qwen_8B_4bit-merged_2epo-mlx-4Bit was converted to MLX format from FritzStack/IRF-Qwen_8B_4bit-merged_2epo using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
!pip install git+https://github.com/Fede-stack/TONYpy.git
from TONY.IRF import IRFPredictor_mlx
text = 'Some days I keep living, even though I feel completely alone in the world'
irf = IRFPredictor_mlx(model_name='FritzStack/IRF-QWEN8B-mlx-Q4')
irf.highlight_evidence_IRF(text)
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Feb 25, 2026
- Updated
- Mar 5, 2026