metadata
license: apache-2.0
quantized_by: bartowski
pipeline_tag: text-generation
Llamacpp Quantizations of Mistral-11b-v0.1
Using llama.cpp release b2440 for quantization.
Original model: https://huggingface.co/Replete-AI/Mistral-11b-v0.1
Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Mistral-11b-v0.1-Q8_0.gguf | Q8_0 | 11.86GB | Extremely high quality, generally unneeded but max available quant. |
| Mistral-11b-v0.1-Q6_K.gguf | Q6_K | 9.16GB | Very high quality, near perfect, recommended. |
| Mistral-11b-v0.1-Q5_K_M.gguf | Q5_K_M | 7.90GB | High quality, very usable. |
| Mistral-11b-v0.1-Q5_K_S.gguf | Q5_K_S | 7.69GB | High quality, very usable. |
| Mistral-11b-v0.1-Q5_0.gguf | Q5_0 | 7.69GB | High quality, older format, generally not recommended. |
| Mistral-11b-v0.1-Q4_K_M.gguf | Q4_K_M | 6.72GB | Good quality, similar to 4.25 bpw. |
| Mistral-11b-v0.1-Q4_K_S.gguf | Q4_K_S | 6.36GB | Slightly lower quality with small space savings. |
| Mistral-11b-v0.1-Q4_0.gguf | Q4_0 | 6.31GB | Decent quality, older format, generally not recommended. |
| Mistral-11b-v0.1-Q3_K_L.gguf | Q3_K_L | 5.87GB | Lower quality but usable, good for low RAM availability. |
| Mistral-11b-v0.1-Q3_K_M.gguf | Q3_K_M | 5.40GB | Even lower quality. |
| Mistral-11b-v0.1-Q3_K_S.gguf | Q3_K_S | 4.85GB | Low quality, not recommended. |
| Mistral-11b-v0.1-Q2_K.gguf | Q2_K | 4.16GB | Extremely low quality, not recommended. |
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski