Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


llama3-1.6b-init - GGUF
- Model creator: https://huggingface.co/emozilla/
- Original model: https://huggingface.co/emozilla/llama3-1.6b-init/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [llama3-1.6b-init.Q2_K.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q2_K.gguf) | Q2_K | 0.65GB |
| [llama3-1.6b-init.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.IQ3_XS.gguf) | IQ3_XS | 0.72GB |
| [llama3-1.6b-init.IQ3_S.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.IQ3_S.gguf) | IQ3_S | 0.74GB |
| [llama3-1.6b-init.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q3_K_S.gguf) | Q3_K_S | 0.74GB |
| [llama3-1.6b-init.IQ3_M.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.IQ3_M.gguf) | IQ3_M | 0.76GB |
| [llama3-1.6b-init.Q3_K.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q3_K.gguf) | Q3_K | 0.8GB |
| [llama3-1.6b-init.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q3_K_M.gguf) | Q3_K_M | 0.8GB |
| [llama3-1.6b-init.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q3_K_L.gguf) | Q3_K_L | 0.84GB |
| [llama3-1.6b-init.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.IQ4_XS.gguf) | IQ4_XS | 0.87GB |
| [llama3-1.6b-init.Q4_0.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q4_0.gguf) | Q4_0 | 0.91GB |
| [llama3-1.6b-init.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.IQ4_NL.gguf) | IQ4_NL | 0.91GB |
| [llama3-1.6b-init.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q4_K_S.gguf) | Q4_K_S | 0.91GB |
| [llama3-1.6b-init.Q4_K.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q4_K.gguf) | Q4_K | 0.95GB |
| [llama3-1.6b-init.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q4_K_M.gguf) | Q4_K_M | 0.95GB |
| [llama3-1.6b-init.Q4_1.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q4_1.gguf) | Q4_1 | 0.99GB |
| [llama3-1.6b-init.Q5_0.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q5_0.gguf) | Q5_0 | 1.06GB |
| [llama3-1.6b-init.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q5_K_S.gguf) | Q5_K_S | 1.06GB |
| [llama3-1.6b-init.Q5_K.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q5_K.gguf) | Q5_K | 1.08GB |
| [llama3-1.6b-init.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q5_K_M.gguf) | Q5_K_M | 1.08GB |
| [llama3-1.6b-init.Q5_1.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q5_1.gguf) | Q5_1 | 1.14GB |
| [llama3-1.6b-init.Q6_K.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q6_K.gguf) | Q6_K | 1.23GB |
| [llama3-1.6b-init.Q8_0.gguf](https://huggingface.co/RichardErkhov/emozilla_-_llama3-1.6b-init-gguf/blob/main/llama3-1.6b-init.Q8_0.gguf) | Q8_0 | 1.59GB |




Original model description:
Entry not found