--- base_model: NousResearch/Hermes-4-70B base_model_relation: quantized quantized_by: ArtusDev language: - en library_name: transformers license: llama3 pipeline_tag: text-generation tags: - Llama-3.1 - instruct - finetune - reasoning - hybrid-mode - chatml - function calling - tool use - json mode - structured outputs - atropos - dataforge - long context - roleplaying - chat - exl3 ---
EXL3 quants of NousResearch/Hermes-4-70B using exllamav3 for quantization.
| Quant | BPW | Head Bits |
|---|---|---|
| 2.5_H6 | 2.5 | 6 |
| 3.0_H6 | 3.0 | 6 |
| 3.5_H6 | 3.5 | 6 |
| 4.0_H6 | 4.0 | 6 |
| 4.25_H6 | 4.25 | 6 |
| 5.0_H6 | 5.0 | 6 |
| 6.0_H6 | 6.0 | 6 |
| 8.0_H8 | 8.0 | 8 |
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/NousResearch_Hermes-4-70B-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.