--- base_model: OpenBuddy/SimpleChat-72B-V4-Apache2.0 base_model_relation: quantized quantized_by: ArtusDev language: - zh - en - fr - de - ja - ko - it - fi tags: - qwen2.5 - exl3 ---
EXL3 quants of OpenBuddy/SimpleChat-72B-V4-Apache2.0 using exllamav3 for quantization.
| Quant | BPW | Head Bits | Size (GB) |
|---|---|---|---|
| 2.5_H6 | 2.5 | 6 | 25.41 |
| 3.0_H6 | 3.0 | 6 | 29.81 |
| 3.5_H6 | 3.5 | 6 | 34.19 |
| 4.0_H6 | 4.0 | 6 | 38.58 |
| 4.25_H6 | 4.25 | 6 | 40.78 |
| 5.0_H6 | 5.0 | 6 | 47.36 |
| 6.0_H6 | 6.0 | 6 | 56.14 |
| 8.0_H8 | 8.0 | 8 | 74.00 |
You can download quants by targeting specific size using the Hugging Face CLI.
pip install -U "huggingface_hub[cli]"
2. Download a specific quant:
huggingface-cli download ArtusDev/OpenBuddy_SimpleChat-72B-V4-Apache2.0-EXL3 --revision "5.0bpw_H6" --local-dir ./
EXL3 quants can be run with any inference client that supports EXL3, such as TabbyAPI. Refer to documentation for set up instructions.
Made possible with cloud compute from lium.io