Downloads · 30 days
0
Qwen2.5-Coder-7B-Instruct-zse-int4
zse-zllm/Qwen2.5-Coder-7B-Instruct-zse-int4
Qwen2.5-Coder-7B-Instruct-zse-int4 is a machine learning model from zse-zllm. 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.
Pre-converted ZSE model for ultra-fast inference.
Access
Public
Updated Mar 19, 2026
Repo size
5.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zse5.6 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 19, 2026
- Updated
- Mar 19, 2026
- SHA
- 81f22a1f
Base models
Model card
From the Hugging Face model README
Qwen2.5-Coder-7B-Instruct-zse-int4
Pre-converted ZSE model for ultra-fast inference.
Source Model
- Original: Qwen/Qwen2.5-Coder-7B-Instruct
- Quantization: INT4
- File Size: 5.18 GB
- Format: ZSE binary (.zse)
Usage
pip install zllm-zse
# Download and serve
zse pull qwen2.5-coder-7b-instruct
zse serve qwen2.5-coder-7b-instruct
# Or direct
zse serve Qwen2.5-Coder-7B-Instruct-zse-int4.zse
Benefits
- 5x faster cold start compared to HuggingFace loading
- 10-14% less VRAM with ZSE custom INT4 kernels
- Single file — tokenizer and config embedded
- No internet required after download
Benchmarks
See ZSE Documentation for full benchmarks.
Converted with ZSE v1.4.0
- License
- apache-2.0
- Created
- Mar 19, 2026
- Updated
- Mar 19, 2026