bartowski/dolphin-2.8-mistral-7b-v02-GGUF

Llamacpp Quantizations of dolphin-2.8-mistral-7b-v02

Using llama.cpp release b2536 for quantization.

Original model: https://huggingface.co./cognitivecomputations/dolphin-2.8-mistral-7b-v02

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

Filename	Quant type	File Size	Description
dolphin-2.8-mistral-7b-v02-Q8_0.gguf	Q8_0	7.69GB	Extremely high quality, generally unneeded but max available quant.
dolphin-2.8-mistral-7b-v02-Q6_K.gguf	Q6_K	5.94GB	Very high quality, near perfect, recommended.
dolphin-2.8-mistral-7b-v02-Q5_K_M.gguf	Q5_K_M	5.13GB	High quality, very usable.
dolphin-2.8-mistral-7b-v02-Q5_K_S.gguf	Q5_K_S	4.99GB	High quality, very usable.
dolphin-2.8-mistral-7b-v02-Q5_0.gguf	Q5_0	4.99GB	High quality, older format, generally not recommended.
dolphin-2.8-mistral-7b-v02-Q4_K_M.gguf	Q4_K_M	4.36GB	Good quality, uses about 4.83 bits per weight.
dolphin-2.8-mistral-7b-v02-Q4_K_S.gguf	Q4_K_S	4.14GB	Slightly lower quality with small space savings.
dolphin-2.8-mistral-7b-v02-IQ4_NL.gguf	IQ4_NL	4.15GB	Decent quality, similar to Q4_K_S, new method of quanting,
dolphin-2.8-mistral-7b-v02-IQ4_XS.gguf	IQ4_XS	3.94GB	Decent quality, new method with similar performance to Q4.
dolphin-2.8-mistral-7b-v02-Q4_0.gguf	Q4_0	4.10GB	Decent quality, older format, generally not recommended.
dolphin-2.8-mistral-7b-v02-Q3_K_L.gguf	Q3_K_L	3.82GB	Lower quality but usable, good for low RAM availability.
dolphin-2.8-mistral-7b-v02-Q3_K_M.gguf	Q3_K_M	3.51GB	Even lower quality.
dolphin-2.8-mistral-7b-v02-IQ3_M.gguf	IQ3_M	3.28GB	Medium-low quality, new method with decent performance.
dolphin-2.8-mistral-7b-v02-IQ3_S.gguf	IQ3_S	3.18GB	Lower quality, new method with decent performance, recommended over Q3 quants.
dolphin-2.8-mistral-7b-v02-Q3_K_S.gguf	Q3_K_S	3.16GB	Low quality, not recommended.
dolphin-2.8-mistral-7b-v02-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