Downloads · 30 days
2
6% of all-time downloads
Sanctum-core-basic-Qwen2.5-1.5B-Instruct-MNN
tony-novus/Sanctum-core-basic-Qwen2.5-1.5B-Instruct-MNN
Sanctum-core-basic-Qwen2.5-1.5B-Instruct-MNN is a text generation model from tony-novus. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This model is a 4-bit quantized version of the MNN model exported from Qwen2.5-1.5B-Instruct using llmexport.
All-time downloads
35
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.weight868 MB · 99%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Mar 12, 2026
- Updated
- Mar 12, 2026
- SHA
- 12ca6b66
Try a prompt
Model card
From the Hugging Face model README
Qwen2.5-1.5B-Instruct-MNN
Introduction
This model is a 4-bit quantized version of the MNN model exported from Qwen2.5-1.5B-Instruct using llmexport.
Download
# install huggingface
pip install huggingface
# shell download
huggingface download --model 'taobao-mnn/Qwen2.5-1.5B-Instruct-MNN' --local_dir 'path/to/dir'
# SDK download
from huggingface_hub import snapshot_download
model_dir = snapshot_download('taobao-mnn/Qwen2.5-1.5B-Instruct-MNN')
# git clone
git clone https://www.modelscope.cn/taobao-mnn/Qwen2.5-1.5B-Instruct-MNN
Usage
# clone MNN source
git clone https://github.com/alibaba/MNN.git
# compile
cd MNN
mkdir build && cd build
cmake .. -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true -DMNN_BUILD_LLM=true -DMNN_SUPPORT_TRANSFORMER_FUSE=true
make -j
# run
./llm_demo /path/to/Qwen2.5-1.5B-Instruct-MNN/config.json prompt.txt
Document
- Task
- Text Generation
- License
- apache-2.0
- Languages
- en
- Created
- Mar 12, 2026
- Updated
- Mar 12, 2026