Llamacpp Quantizations of OpenHercules-2.5-Mistral-7B
Using llama.cpp commit fa97464 for quantization.
Original model: https://huggingface.co/hydra-project/OpenHercules-2.5-Mistral-7B
Download a file (not the whole branch) from below:
Filename |
Quant type |
File Size |
Description |
OpenHercules-2.5-Mistral-7B-Q8_0.gguf |
Q8_0 |
7.69GB |
Extremely high quality, generally unneeded but max available quant. |
OpenHercules-2.5-Mistral-7B-Q6_K.gguf |
Q6_K |
5.94GB |
Very high quality, near perfect, recommended. |
OpenHercules-2.5-Mistral-7B-Q5_K_M.gguf |
Q5_K_M |
5.13GB |
High quality, very usable. |
OpenHercules-2.5-Mistral-7B-Q5_K_S.gguf |
Q5_K_S |
4.99GB |
High quality, very usable. |
OpenHercules-2.5-Mistral-7B-Q5_0.gguf |
Q5_0 |
4.99GB |
High quality, older format, generally not recommended. |
OpenHercules-2.5-Mistral-7B-Q4_K_M.gguf |
Q4_K_M |
4.36GB |
Good quality, similar to 4.25 bpw. |
OpenHercules-2.5-Mistral-7B-Q4_K_S.gguf |
Q4_K_S |
4.14GB |
Slightly lower quality with small space savings. |
OpenHercules-2.5-Mistral-7B-Q4_0.gguf |
Q4_0 |
4.10GB |
Decent quality, older format, generally not recommended. |
OpenHercules-2.5-Mistral-7B-Q3_K_L.gguf |
Q3_K_L |
3.82GB |
Lower quality but usable, good for low RAM availability. |
OpenHercules-2.5-Mistral-7B-Q3_K_M.gguf |
Q3_K_M |
3.51GB |
Even lower quality. |
OpenHercules-2.5-Mistral-7B-Q3_K_S.gguf |
Q3_K_S |
3.16GB |
Low quality, not recommended. |
OpenHercules-2.5-Mistral-7B-Q2_K.gguf |
Q2_K |
2.71GB |
Extremely low quality, not recommended. |
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski