Downloads · 30 days
18
7% of all-time downloads
Jan-code-4b-bnb-4bit-nf4-dq
manu02/Jan-code-4b-bnb-4bit-nf4-dq
Jan-code-4b-bnb-4bit-nf4-dq is a text generation model from manu02. 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.
This model is a 4-bit quantized version of the original janhq/Jan-code-4b model, optimized for reduced memory usage while maintaining performance.
All-time downloads
243
Public
Parameters
4.5B
3.4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.4 GB · 100%
Parameter types
How the weights are stored.
U83.7B · 83%
Try a prompt
Base models
Model card
From the Hugging Face model README
Jan-code-4b (Quantized)
Description
This model is a 4-bit quantized version of the original janhq/Jan-code-4b model, optimized for reduced memory usage while maintaining performance.
Quantization Details
- Quantization Type: 4-bit
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
- bnb_4bit_quant_storage: uint8
- Original Footprint: 8044.94 MB (BFLOAT16)
- Quantized Footprint: 3372.88 MB (UINT8)
- Memory Reduction: 58.1%
Usage
from transformers import AutoModel, AutoTokenizer
model_name = "Jan-code-4b-bnb-4bit-nf4"
model = AutoModel.from_pretrained(
"manu02/Jan-code-4b-bnb-4bit-nf4",
)
tokenizer = AutoTokenizer.from_pretrained("manu02/Jan-code-4b-bnb-4bit-nf4", use_fast=True)
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026