Llamacpp Quantizations of openbuddy-mistral-7b-v19.1-4k
Using llama.cpp commit fa97464 for quantization.
Original model: https://huggingface.co/OpenBuddy/openbuddy-mistral-7b-v19.1-4k
Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| openbuddy-mistral-7b-v19.1-4k-Q8_0.gguf | Q8_0 | 7.73GB | Extremely high quality, generally unneeded but max available quant. |
| openbuddy-mistral-7b-v19.1-4k-Q6_K.gguf | Q6_K | 5.97GB | Very high quality, near perfect, recommended. |
| openbuddy-mistral-7b-v19.1-4k-Q5_K_M.gguf | Q5_K_M | 5.15GB | High quality, very usable. |
| openbuddy-mistral-7b-v19.1-4k-Q5_K_S.gguf | Q5_K_S | 5.02GB | High quality, very usable. |
| openbuddy-mistral-7b-v19.1-4k-Q5_0.gguf | Q5_0 | 5.02GB | High quality, older format, generally not recommended. |
| openbuddy-mistral-7b-v19.1-4k-Q4_K_M.gguf | Q4_K_M | 4.39GB | Good quality, similar to 4.25 bpw. |
| openbuddy-mistral-7b-v19.1-4k-Q4_K_S.gguf | Q4_K_S | 4.16GB | Slightly lower quality with small space savings. |
| openbuddy-mistral-7b-v19.1-4k-Q4_0.gguf | Q4_0 | 4.13GB | Decent quality, older format, generally not recommended. |
| openbuddy-mistral-7b-v19.1-4k-Q3_K_L.gguf | Q3_K_L | 3.84GB | Lower quality but usable, good for low RAM availability. |
| openbuddy-mistral-7b-v19.1-4k-Q3_K_M.gguf | Q3_K_M | 3.54GB | Even lower quality. |
| openbuddy-mistral-7b-v19.1-4k-Q3_K_S.gguf | Q3_K_S | 3.18GB | Low quality, not recommended. |
| openbuddy-mistral-7b-v19.1-4k-Q2_K.gguf | Q2_K | 2.74GB | Extremely low quality, not recommended. |
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
- Downloads last month
- 239
Model size
7.28B params
Architecture
llama