Downloads · 30 days
4
6% of all-time downloads
Qwen__Qwen3-4B-Thinking-2507_RTN_w3g128
quantpa/Qwen__Qwen3-4B-Thinking-2507_RTN_w3g128
Qwen__Qwen3-4B-Thinking-2507_RTN_w3g128 is a machine learning model from quantpa. 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 3-bit RTN (Round-To-Nearest) quantized version of Qwen/Qwen3-4B-Thinking-2507.
All-time downloads
72
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jan 21, 2026
- Updated
- Jan 21, 2026
- SHA
- 69d610e9
Base models
Model card
From the Hugging Face model README
Qwen__Qwen3-4B-Thinking-2507_RTN_w3g128
This is a 3-bit RTN (Round-To-Nearest) quantized version of Qwen/Qwen3-4B-Thinking-2507.
Quantization Details
- Method: RTN (Round-To-Nearest)
- Bits: 3-bit
- Group Size: 128
- Base Model: Qwen/Qwen3-4B-Thinking-2507
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "quantpa/Qwen__Qwen3-4B-Thinking-2507_RTN_w3g128"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
# Use the model for inference
Model Details
- Quantization: RTN 3-bit
- Original Model: Qwen/Qwen3-4B-Thinking-2507
- Quantized by: quantpa
- Type
- qwen3
- License
- apache-2.0
- Created
- Jan 21, 2026
- Updated
- Jan 21, 2026