Llamacpp Quantizations of EveryoneLLM-7b-Gemma-Base
Using llama.cpp release b2354 for quantization.
Original model: https://huggingface.co/rombodawg/EveryoneLLM-7b-Gemma-Base
Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| EveryoneLLM-7b-Gemma-Base-Q8_0.gguf | Q8_0 | 9.07GB | Extremely high quality, generally unneeded but max available quant. |
| EveryoneLLM-7b-Gemma-Base-Q6_K.gguf | Q6_K | 7.01GB | Very high quality, near perfect, recommended. |
| EveryoneLLM-7b-Gemma-Base-Q5_K_M.gguf | Q5_K_M | 6.04GB | High quality, very usable. |
| EveryoneLLM-7b-Gemma-Base-Q5_K_S.gguf | Q5_K_S | 5.87GB | High quality, very usable. |
| EveryoneLLM-7b-Gemma-Base-Q5_0.gguf | Q5_0 | 5.87GB | High quality, older format, generally not recommended. |
| EveryoneLLM-7b-Gemma-Base-Q4_K_M.gguf | Q4_K_M | 5.12GB | Good quality, similar to 4.25 bpw. |
| EveryoneLLM-7b-Gemma-Base-Q4_K_S.gguf | Q4_K_S | 4.84GB | Slightly lower quality with small space savings. |
| EveryoneLLM-7b-Gemma-Base-Q4_0.gguf | Q4_0 | 4.80GB | Decent quality, older format, generally not recommended. |
| EveryoneLLM-7b-Gemma-Base-Q3_K_L.gguf | Q3_K_L | 4.40GB | Lower quality but usable, good for low RAM availability. |
| EveryoneLLM-7b-Gemma-Base-Q3_K_M.gguf | Q3_K_M | 4.06GB | Even lower quality. |
| EveryoneLLM-7b-Gemma-Base-Q3_K_S.gguf | Q3_K_S | 3.67GB | Low quality, not recommended. |
| EveryoneLLM-7b-Gemma-Base-Q2_K.gguf | Q2_K | 3.09GB | Extremely low quality, not recommended. |
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
- Downloads last month
- 143