Modelpublic

bartowski/starcoder2-15b-instruct-GGUF

sourceHugging Facebigcode-openrail-mupdated 3y agoView on Hugging Face

5likes869downloads

Model Card

Llamacpp Quantizations of starcoder2-15b-instruct

Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2354">b2354</a> for quantization.

Original model: https://huggingface.co/TechxGenus/starcoder2-15b-instruct

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

Filename	Quant type	File Size	Description
starcoder2-15b-instruct-Q8_0.gguf	Q8_0	16.96GB	Extremely high quality, generally unneeded but max available quant.
starcoder2-15b-instruct-Q6_K.gguf	Q6_K	13.10GB	Very high quality, near perfect, recommended.
starcoder2-15b-instruct-Q5_K_M.gguf	Q5KM	11.43GB	High quality, very usable.
starcoder2-15b-instruct-Q5_K_S.gguf	Q5KS	11.02GB	High quality, very usable.
starcoder2-15b-instruct-Q5_0.gguf	Q5_0	11.02GB	High quality, older format, generally not recommended.
starcoder2-15b-instruct-Q4_K_M.gguf	Q4KM	9.86GB	Good quality, similar to 4.25 bpw.
starcoder2-15b-instruct-Q4_K_S.gguf	Q4KS	9.25GB	Slightly lower quality with small space savings.
starcoder2-15b-instruct-Q4_0.gguf	Q4_0	9.06GB	Decent quality, older format, generally not recommended.
starcoder2-15b-instruct-Q3_K_L.gguf	Q3KL	8.96GB	Lower quality but usable, good for low RAM availability.
starcoder2-15b-instruct-Q3_K_M.gguf	Q3KM	8.10GB	Even lower quality.
starcoder2-15b-instruct-Q3_K_S.gguf	Q3KS	6.98GB	Low quality, not recommended.
starcoder2-15b-instruct-Q2_K.gguf	Q2_K	6.19GB	Extremely low quality, not recommended.

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