Modelpublic

bartowski/bigstral-12b-32k-8xMoE-GGUF

sourceHugging Faceupdated 3y agoView on Hugging Face

2likes448downloads

Model Card

Llamacpp Quantizations of bigstral-12b-32k-8xMoE

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/bartowski/bigstral-12b-32k-8xMoE

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

Filename	Quant type	File Size	Description
bigstral-12b-32k-8xMoE-Q8_0.gguf	Q8_0	86.63GB	Extremely high quality, generally unneeded but max available quant.
bigstral-12b-32k-8xMoE-Q6_K.gguf	Q6_K	67.00GB	Very high quality, near perfect, recommended.
bigstral-12b-32k-8xMoE-Q5_K_M.gguf	Q5KM	58.00GB	High quality, very usable.
bigstral-12b-32k-8xMoE-Q5_K_S.gguf	Q5KS	56.25GB	High quality, very usable.
bigstral-12b-32k-8xMoE-Q5_0.gguf	Q5_0	56.25GB	High quality, older format, generally not recommended.
bigstral-12b-32k-8xMoE-Q4_K_M.gguf	Q4KM	49.60GB	Good quality, similar to 4.25 bpw.
bigstral-12b-32k-8xMoE-Q4_K_S.gguf	Q4KS	46.70GB	Slightly lower quality with small space savings.
bigstral-12b-32k-8xMoE-Q4_0.gguf	Q4_0	46.13GB	Decent quality, older format, generally not recommended.
bigstral-12b-32k-8xMoE-Q3_K_L.gguf	Q3KL	42.16GB	Lower quality but usable, good for low RAM availability.
bigstral-12b-32k-8xMoE-Q3_K_M.gguf	Q3KM	39.30GB	Even lower quality.
bigstral-12b-32k-8xMoE-Q3_K_S.gguf	Q3KS	35.62GB	Low quality, not recommended.
bigstral-12b-32k-8xMoE-Q2_K.gguf	Q2_K	30.17GB	Extremely low quality, not recommended.

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