Downloads · 30 days
14
10% of all-time downloads
Jan-nano-128k-W8A8
dolfsai/Jan-nano-128k-W8A8
Jan-nano-128k-W8A8 is a text generation model from dolfsai. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This is a compressed version of Menlo/Jan-nano-128k using llm-compressor with the following scheme: W8A8 Usage instructions and details here
All-time downloads
138
Public
Parameters
4.4B
5.2 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors5.2 GB · 100%
Parameter types
How the weights are stored.
I83.6B · 82%
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
dolfsai/Jan-nano-128k-W8A8
This is a compressed version of Menlo/Jan-nano-128k using llm-compressor with the following scheme: W8A8 Usage instructions and details here
Model Details
- Original Model: Menlo/Jan-nano-128k
- Quantization Method: GPTQ
- Compression Libraries: llm-compressor
- Calibration Dataset: ultrachat_200k (1024 samples)
- Optimized For: Inference with vLLM
- License: same as original model
- Task
- Text Generation
- Type
- qwen3
- License
- apache-2.0
- Languages
- en, es
- Created
- Sep 27, 2025
- Updated
- Sep 29, 2025