bartowski/Fimbulvetr-Kuro-Lotus-10.7B-GGUF

Llamacpp Quantizations of Fimbulvetr-Kuro-Lotus-10.7B

Using llama.cpp release b2440 for quantization.

Original model: https://huggingface.co/saishf/Fimbulvetr-Kuro-Lotus-10.7B

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

Filename	Quant type	File Size	Description
Fimbulvetr-Kuro-Lotus-10.7B-Q8_0.gguf	Q8_0	11.40GB	Extremely high quality, generally unneeded but max available quant.
Fimbulvetr-Kuro-Lotus-10.7B-Q6_K.gguf	Q6_K	8.80GB	Very high quality, near perfect, recommended.
Fimbulvetr-Kuro-Lotus-10.7B-Q5_K_M.gguf	Q5_K_M	7.59GB	High quality, very usable.
Fimbulvetr-Kuro-Lotus-10.7B-Q5_K_S.gguf	Q5_K_S	7.39GB	High quality, very usable.
Fimbulvetr-Kuro-Lotus-10.7B-Q5_0.gguf	Q5_0	7.39GB	High quality, older format, generally not recommended.
Fimbulvetr-Kuro-Lotus-10.7B-Q4_K_M.gguf	Q4_K_M	6.46GB	Good quality, similar to 4.25 bpw.
Fimbulvetr-Kuro-Lotus-10.7B-Q4_K_S.gguf	Q4_K_S	6.11GB	Slightly lower quality with small space savings.
Fimbulvetr-Kuro-Lotus-10.7B-Q4_0.gguf	Q4_0	6.07GB	Decent quality, older format, generally not recommended.
Fimbulvetr-Kuro-Lotus-10.7B-Q3_K_L.gguf	Q3_K_L	5.65GB	Lower quality but usable, good for low RAM availability.
Fimbulvetr-Kuro-Lotus-10.7B-Q3_K_M.gguf	Q3_K_M	5.19GB	Even lower quality.
Fimbulvetr-Kuro-Lotus-10.7B-Q3_K_S.gguf	Q3_K_S	4.66GB	Low quality, not recommended.
Fimbulvetr-Kuro-Lotus-10.7B-Q2_K.gguf	Q2_K	4.00GB	Extremely low quality, not recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski