bartowski/Starling-LM-10.7B-beta-GGUF

Llamacpp Quantizations of Starling-LM-10.7B-beta

Using llama.cpp release b2589 for quantization.

Original model: https://huggingface.co/ddh0/Starling-LM-10.7B-beta

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

Filename	Quant type	File Size	Description
Starling-LM-10.7B-beta-Q8_0.gguf	Q8_0	11.40GB	Extremely high quality, generally unneeded but max available quant.
Starling-LM-10.7B-beta-Q6_K.gguf	Q6_K	8.80GB	Very high quality, near perfect, recommended.
Starling-LM-10.7B-beta-Q5_K_M.gguf	Q5_K_M	7.59GB	High quality, very usable.
Starling-LM-10.7B-beta-Q5_K_S.gguf	Q5_K_S	7.39GB	High quality, very usable.
Starling-LM-10.7B-beta-Q5_0.gguf	Q5_0	7.39GB	High quality, older format, generally not recommended.
Starling-LM-10.7B-beta-Q4_K_M.gguf	Q4_K_M	6.46GB	Good quality, uses about 4.83 bits per weight.
Starling-LM-10.7B-beta-Q4_K_S.gguf	Q4_K_S	6.11GB	Slightly lower quality with small space savings.
Starling-LM-10.7B-beta-IQ4_NL.gguf	IQ4_NL	6.14GB	Decent quality, similar to Q4_K_S, new method of quanting,
Starling-LM-10.7B-beta-IQ4_XS.gguf	IQ4_XS	5.82GB	Decent quality, new method with similar performance to Q4.
Starling-LM-10.7B-beta-Q4_0.gguf	Q4_0	6.07GB	Decent quality, older format, generally not recommended.
Starling-LM-10.7B-beta-Q3_K_L.gguf	Q3_K_L	5.65GB	Lower quality but usable, good for low RAM availability.
Starling-LM-10.7B-beta-Q3_K_M.gguf	Q3_K_M	5.19GB	Even lower quality.
Starling-LM-10.7B-beta-IQ3_M.gguf	IQ3_M	4.84GB	Medium-low quality, new method with decent performance.
Starling-LM-10.7B-beta-IQ3_S.gguf	IQ3_S	4.69GB	Lower quality, new method with decent performance, recommended over Q3 quants.
Starling-LM-10.7B-beta-Q3_K_S.gguf	Q3_K_S	4.66GB	Low quality, not recommended.
Starling-LM-10.7B-beta-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