JiRack Coder Reasoning 14B INT4
A fast and efficient coding assistant with a clean built-in web UI, powered by Qwen3.0-Coder-14B-Instruct base and optimized using Microsoft ONNX Runtime.
Quick Start
Watch the JiRack Coder 14B in action: DEMO: JiRack Coder Reasoning 14B Web UI
Run with Docker
--Default CPU--
- docker run -d
--name jirack_coder_reasoning_14b
-p 7869:7869
--restart unless-stopped
cmsmanhattan/jirack_coder_14b_int4_qwenbase:latest
--Multi CPU--
- docker run -d
--name jirack_coder_reasoning_14b
-p 7869:7869
--restart unless-stopped
--memory=20g
--cpus=12
cmsmanhattan/jirack_coder_14b_int4_qwenbase:latest
---GPU-- -- comming soon
- docker run -d
--name jirack_coder_reasoning_14b
-p 7869:7869
--gpus all
--restart unless-stopped
cmsmanhattan/jirack_coder_14b_int4_gpu_qwenbase:latest
Access the UI
Once the container is running, open your browser and navigate to:
http://localhost:7869
This opens the JiRack Coder UI — a clean web interface designed for coding.
Changing the Port
The listening port can be easily modified directly from the Settings panel within the JiRack Coder UI.
Licensing
- The JiRack Coder 14B model is provided under a commercial license. It is about $12 for year per user.
- All JiRack UI clients are provided under a commercial license.
- However, the UI clients can be used for free when running together with the official JiRack Docker containers, as long as they are not redistributed separately.
JiRack Coder 32B is available exclusively under a commercial enterprise license.
For commercial licensing, cluster deployment, or enterprise use of the JiRack Coder 32B and JiRack Coder 14B, please contact us.
- JiRack MS Windows 11 Desktop chat client with ollama API setup: https://huggingface.co/kgrabko/JiRackTernary_1b/resolve/main/jirack-chat.zip
- Live email chat with model via support@cmsmanhattan.com
Hardware Recommendations for AMD Systems
It is more heavy then JiRack Coder 7B INT8
Recommended Hardware for JiRack Coder Reasoning 14B INT4. It is one docker container
| Use Case | CPU | GPU (ROCm) | VRAM / RAM | Expected Speed | Recommendation |
|---|---|---|---|---|---|
| Recommended | Ryzen 7 7700 / 9700X | RX 7900 XTX / 7900 XT | 24GB VRAM | 50-75 tokens/s | Best choice |
| High Performance | Ryzen 9 7950X / 9950X | RX 7900 XTX | 24GB+ VRAM | 65-90 tokens/s | Excellent |
| Enterprise | EPYC 7003/9004 series | MI300X or 2x RX 7900 XTX | 48GB+ VRAM | 90-140 tokens/s | For 32B model |
| Budget Option | Ryzen 5 7600 / 9600X | RX 7800 XT (16GB) | 16GB VRAM | 35-50 tokens/s | Acceptable |
Important Memory Notes
Even though the 14B INT4 model itself takes approximately 5–6 GB, we recommend at least 24GB VRAM for the following reasons:
- KV-cache consumption during generation (especially with long context)
- ONNX Runtime overhead and temporary buffers
- System stability and to avoid Out of Memory errors
- Room for larger context windows
Minimum recommended: 24GB VRAM (RX 7900 series)
Ideal: 24–32GB VRAM
For pure CPU inference (no GPU), we recommend at least 64GB system RAM (Ryzen 9 7950X/9950X).
I will use the default model in full FP32 precision for quantization, allowing us to find the optimal balance between model size and performance.
📧 Contact & Licensing
For joint venture opportunities, hardware integration, or licensing inquiries:
- Email: grabko@cmsmanhattan.com
- Phone: +1 (516) 777-0945
- Location: New York, USA