Downloads · 30 days
5
15% of all-time downloads
Qwen2.5-0.5B-bnb-4bit
BondingAI/Qwen2.5-0.5B-bnb-4bit
Qwen2.5-0.5B-bnb-4bit is a machine learning model from BondingAI. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a 4-bit BitsAndBytes quantized model for HuggingFace transformers.
All-time downloads
34
Public
Parameters
505M
469 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors457 MB · 97%
Parameter types
How the weights are stored.
U8369M · 73%
Base models
Model card
From the Hugging Face model README
Qwen2.5-0.5B - BitsAndBytes Quantized Model
This is a 4-bit BitsAndBytes quantized model for HuggingFace transformers.
Model Details
- Base Model: Qwen/Qwen2.5-0.5B
- Quantization: BitsAndBytes 4-bit
- Framework: transformers (CUDA)
Usage with transformers
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
bnb_config = BitsAndBytesConfig(load_in_4bit=True)
model = AutoModelForCausalLM.from_pretrained(
"BondingAI/Qwen2.5-0.5B-bnb-4bit",
quantization_config=bnb_config,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("BondingAI/Qwen2.5-0.5B-bnb-4bit")
License
Please refer to the original model card for licensing information.
- Type
- qwen2
- License
- apache-2.0
- Created
- Feb 24, 2026
- Updated
- Feb 24, 2026