CoolFace
Modelpublic

bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-GGUF

sourceHugging Facecc-by-nc-4.0updated 3y agoView on Hugging Face
0likes983downloads
Model Card

Llamacpp Quantizations of StarlingMonarchWestlake_Garten-7B-v0.1

Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.

Original model: https://huggingface.co/giraffe176/StarlingMonarchWestlake_Garten-7B-v0.1

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

FilenameQuant typeFile SizeDescription
Starling_Monarch_Westlake_Garten-7B-v0.1-Q8_0.ggufQ8_07.69GBExtremely high quality, generally unneeded but max available quant.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q6_K.ggufQ6_K5.94GBVery high quality, near perfect, recommended.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q5_K_M.ggufQ5KM5.13GBHigh quality, very usable.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q5_K_S.ggufQ5KS4.99GBHigh quality, very usable.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q5_0.ggufQ5_04.99GBHigh quality, older format, generally not recommended.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q4_K_M.ggufQ4KM4.36GBGood quality, similar to 4.25 bpw.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q4_K_S.ggufQ4KS4.14GBSlightly lower quality with small space savings.
Starling_Monarch_Westlake_Garten-7B-v0.1-IQ4_NL.ggufIQ4_NL4.15GBGood quality, similar to Q4KS, new method of quanting,
Starling_Monarch_Westlake_Garten-7B-v0.1-IQ4_XS.ggufIQ4_XS3.94GBDecent quality, new method with similar performance to Q4.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q4_0.ggufQ4_04.10GBDecent quality, older format, generally not recommended.
Starling_Monarch_Westlake_Garten-7B-v0.1-IQ3_M.ggufIQ3_M3.28GBMedium-low quality, new method with decent performance.
Starling_Monarch_Westlake_Garten-7B-v0.1-IQ3_S.ggufIQ3_S3.18GBLower quality, new method with decent performance, recommended over Q3 quants.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q3_K_L.ggufQ3KL3.82GBLower quality but usable, good for low RAM availability.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q3_K_M.ggufQ3KM3.51GBEven lower quality.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q3_K_S.ggufQ3KS3.16GBLow quality, not recommended.
Starling_Monarch_Westlake_Garten-7B-v0.1-Q2_K.ggufQ2_K2.71GBExtremely low quality, not recommended.

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