Edit model card

Llamacpp Quantizations of merlinite-7b

Using llama.cpp commit fa97464 for quantization.

Original model: https://huggingface.co/ibm/merlinite-7b

Download a file (not the whole branch) from below:

Filename Quant type File Size Description
merlinite-7b-Q8_0.gguf Q8_0 7.69GB Extremely high quality, generally unneeded but max available quant.
merlinite-7b-Q6_K.gguf Q6_K 5.94GB Very high quality, near perfect, recommended.
merlinite-7b-Q5_K_M.gguf Q5_K_M 5.13GB High quality, very usable.
merlinite-7b-Q5_K_S.gguf Q5_K_S 4.99GB High quality, very usable.
merlinite-7b-Q5_0.gguf Q5_0 4.99GB High quality, older format, generally not recommended.
merlinite-7b-Q4_K_M.gguf Q4_K_M 4.36GB Good quality, similar to 4.25 bpw.
merlinite-7b-Q4_K_S.gguf Q4_K_S 4.14GB Slightly lower quality with small space savings.
merlinite-7b-Q4_0.gguf Q4_0 4.10GB Decent quality, older format, generally not recommended.
merlinite-7b-Q3_K_L.gguf Q3_K_L 3.82GB Lower quality but usable, good for low RAM availability.
merlinite-7b-Q3_K_M.gguf Q3_K_M 3.51GB Even lower quality.
merlinite-7b-Q3_K_S.gguf Q3_K_S 3.16GB Low quality, not recommended.
merlinite-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

Downloads last month
62
GGUF
Model size
7.24B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for bartowski/merlinite-7b-GGUF

Quantized
(168)
this model