bartowski/Replete-Coder-V2-Llama-3.1-8b-GGUF-torrent
bartowski/Replete-Coder-V2-Llama-3.1-8b-GGUF · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
| Filename | Quant Type | File Size | Split | Description |
|---|---|---|---|---|
| Replete-Coder-V2-Llama-3.1-8b-Q6_K_L.gguf | Q6_K_L | 6.85GB | False | Very high quality, near perfect, recommended. Uses Q8_0 for embed and output weights. |
| Replete-Coder-V2-Llama-3.1-8b-Q6_K.gguf | Q6_K | 6.60GB | False | Very high quality, near perfect, recommended. |
| Replete-Coder-V2-Llama-3.1-8b-Q5_K_L.gguf | Q5_K_L | 6.06GB | False | High quality, recommended. Uses Q8_0 for embed and output weights. |
| Replete-Coder-V2-Llama-3.1-8b-Q5_K_M.gguf | Q5_K_M | 5.73GB | False | High quality, recommended. |
| Replete-Coder-V2-Llama-3.1-8b-Q4_K_L.gguf | Q4_K_L | 5.31GB | False | Good quality, recommended. Uses Q8_0 for embed and output weights. |
| Replete-Coder-V2-Llama-3.1-8b-Q4_K_M.gguf | Q4_K_M | 4.92GB | False | Good quality, default size for most use cases, recommended. |
| Replete-Coder-V2-Llama-3.1-8b-IQ4_XS.gguf | IQ4_XS | 4.45GB | False | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Replete-Coder-V2-Llama-3.1-8b-Q3_K_L.gguf | Q3_K_L | 4.32GB | False | Lower quality but usable, good for low RAM availability. Uses Q8_0 for embed and output weights. |
| Replete-Coder-V2-Llama-3.1-8b-Q2_K_L.gguf | Q2_K_L | 3.69GB | False | Very low quality but surprisingly usable. Uses Q8_0 for embed and output weights. |