EXL3 Quants of TheDrummer/Anubis-70B-v1.1
EXL3 quants of TheDrummer/Anubis-70B-v1.1 using exllamav3 for quantization.
Quants
| Quant(Revision) | Bits per Weight | 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_H6 | 8.0 | 6 |
| 8.0_H8 | 8.0 | 8 |
Downloading quants with huggingface-cli
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ArtusDev/TheDrummer_Anubis-70B-v1.1-EXL3
Base model
meta-llama/Llama-3.1-70B Finetuned
meta-llama/Llama-3.3-70B-Instruct Finetuned
TheDrummer/Anubis-70B-v1.1