--- tags: - GGUF base_model: - seyf1elislam/Franky_westKunai-hermes-1-7b --- # Franky_westKunai-hermes-1-7b - Model creator: [seyf1elislam](https://huggingface.co/seyf1elislam) - Original model: [Franky_westKunai-hermes-1-7b](https://huggingface.co/seyf1elislam/Franky_westKunai-hermes-1-7b) ## Description This repo contains GGUF format model files for [seyf1elislam's Franky_westKunai-hermes-1-7b ](https://huggingface.co/seyf1elislam/Franky_westKunai-hermes-1-7b). ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [franky_westkunai-hermes-1-7b.Q2_K.gguf ](https://huggingface.co/seyf1elislam/Franky_westKunai-hermes-1-7b-GGUF/blob/main/franky_westkunai-hermes-1-7b.Q2_K.gguf ) | Q2_K | 2 | 2.72 GB| 5.22 GB | significant quality loss - not recommended for most purposes | | [franky_westkunai-hermes-1-7b.Q3_K_M.gguf ](https://huggingface.co/seyf1elislam/Franky_westKunai-hermes-1-7b-GGUF/blob/main/franky_westkunai-hermes-1-7b.Q3_K_M.gguf ) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss | | [franky_westkunai-hermes-1-7b.Q4_K_M.gguf ](https://huggingface.co/seyf1elislam/Franky_westKunai-hermes-1-7b-GGUF/blob/main/franky_westkunai-hermes-1-7b.Q4_K_M.gguf ) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended | | [franky_westkunai-hermes-1-7b.Q5_K_M.gguf ](https://huggingface.co/seyf1elislam/Franky_westKunai-hermes-1-7b-GGUF/blob/main/franky_westkunai-hermes-1-7b.Q5_K_M.gguf ) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended | | [franky_westkunai-hermes-1-7b.Q6_K.gguf ](https://huggingface.co/seyf1elislam/Franky_westKunai-hermes-1-7b-GGUF/blob/main/franky_westkunai-hermes-1-7b.Q6_K.gguf ) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss | | [franky_westkunai-hermes-1-7b.Q8_0.gguf ](https://huggingface.co/seyf1elislam/Franky_westKunai-hermes-1-7b-GGUF/blob/main/franky_westkunai-hermes-1-7b.Q8_0.gguf ) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |