Update README.md
Browse files
README.md
CHANGED
|
@@ -49,7 +49,37 @@ The listening port can be easily modified directly from the **Settings** panel w
|
|
| 49 |
|
| 50 |
For commercial licensing, cluster deployment, or enterprise use of the JiRack Coder 32B and JiRack Coder 14B , please contact us.
|
| 51 |
- JiRack MS Windows 11 Desktop chat client with ollama API setup : https://huggingface.co/kgrabko/JiRackTernary_1b/resolve/main/jirack-chat.zip
|
| 52 |
-
- Live email chat with model via support@cmsmanhattan.com
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
## 📧 Contact & Licensing
|
| 55 |
For joint venture opportunities, hardware integration, or licensing inquiries:
|
|
|
|
| 49 |
|
| 50 |
For commercial licensing, cluster deployment, or enterprise use of the JiRack Coder 32B and JiRack Coder 14B , please contact us.
|
| 51 |
- JiRack MS Windows 11 Desktop chat client with ollama API setup : https://huggingface.co/kgrabko/JiRackTernary_1b/resolve/main/jirack-chat.zip
|
| 52 |
+
- Live email chat with model via support@cmsmanhattan.com
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
## Hardware Recommendations for AMD Systems
|
| 56 |
+
|
| 57 |
+
Here's a clear and practical hardware recommendation for running **JiRack Coder 7B** (INT8 / INT4) on AMD platforms:
|
| 58 |
+
|
| 59 |
+
### Best AMD Hardware Recommendations
|
| 60 |
+
|
| 61 |
+
| Use Case | Recommended CPU | Recommended GPU (ROCm) | RAM | Expected Speed | Notes |
|
| 62 |
+
|-----------------------|----------------------------------|--------------------------------------|----------|----------------------|---------------------------|
|
| 63 |
+
| **Good Performance** | Ryzen 7 7700 / 9700X | RX 7900 XTX / 7900 XT (24GB) | 32GB+ | 45-70 tokens/s | Best balance |
|
| 64 |
+
| **Very Good** | Ryzen 9 7950X / 9950X | RX 7900 XTX (24GB) | 64GB | 55-85 tokens/s | Strong choice |
|
| 65 |
+
| **Enterprise / Fast** | EPYC 7003/9004 series | Instinct MI300X or 2x RX 7900 XTX | 128GB+ | 80-120+ tokens/s | For 32B model too |
|
| 66 |
+
| **Budget / Decent** | Ryzen 5 7600 / 9600X | RX 7800 XT (16GB) | 32GB | 35-50 tokens/s | Acceptable |
|
| 67 |
+
|
| 68 |
+
### Key Recommendations (AMD)
|
| 69 |
+
|
| 70 |
+
**Top Pick (Best Price/Performance):**
|
| 71 |
+
- **CPU**: Ryzen 7 9700X or Ryzen 9 7950X
|
| 72 |
+
- **GPU**: Radeon RX 7900 XTX (24GB VRAM) — strongly recommended
|
| 73 |
+
- **RAM**: 64GB DDR5
|
| 74 |
+
|
| 75 |
+
**Important Notes:**
|
| 76 |
+
- ROCm support is decent on RX 7000 series, but less stable than NVIDIA.
|
| 77 |
+
- For pure CPU inference, Ryzen 9 7950X / 9950X with 64GB+ RAM performs excellently.
|
| 78 |
+
- The **INT4** version runs noticeably faster than INT8 on AMD CPUs.
|
| 79 |
+
|
| 80 |
+
---
|
| 81 |
+
|
| 82 |
+
Would you like me to add recommendations based on your budget (e.g. under $1500, mid-range, high-end)?
|
| 83 |
|
| 84 |
## 📧 Contact & Licensing
|
| 85 |
For joint venture opportunities, hardware integration, or licensing inquiries:
|