CoolFace
Modelpublic

bartowski/Hyperion-2.0-Mistral-7B-GGUF

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes560downloads
Model Card

Llamacpp Quantizations of Hyperion-2.0-Mistral-7B

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/Locutusque/Hyperion-2.0-Mistral-7B

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

FilenameQuant typeFile SizeDescription
Hyperion-2.0-Mistral-7B-Q8_0.ggufQ8_07.69GBExtremely high quality, generally unneeded but max available quant.
Hyperion-2.0-Mistral-7B-Q6_K.ggufQ6_K5.94GBVery high quality, near perfect, recommended.
Hyperion-2.0-Mistral-7B-Q5_K_M.ggufQ5KM5.13GBHigh quality, very usable.
Hyperion-2.0-Mistral-7B-Q5_K_S.ggufQ5KS4.99GBHigh quality, very usable.
Hyperion-2.0-Mistral-7B-Q5_0.ggufQ5_04.99GBHigh quality, older format, generally not recommended.
Hyperion-2.0-Mistral-7B-Q4_K_M.ggufQ4KM4.36GBGood quality, similar to 4.25 bpw.
Hyperion-2.0-Mistral-7B-Q4_K_S.ggufQ4KS4.14GBSlightly lower quality with small space savings.
Hyperion-2.0-Mistral-7B-Q4_0.ggufQ4_04.10GBDecent quality, older format, generally not recommended.
Hyperion-2.0-Mistral-7B-Q3_K_L.ggufQ3KL3.82GBLower quality but usable, good for low RAM availability.
Hyperion-2.0-Mistral-7B-Q3_K_M.ggufQ3KM3.51GBEven lower quality.
Hyperion-2.0-Mistral-7B-Q3_K_S.ggufQ3KS3.16GBLow quality, not recommended.
Hyperion-2.0-Mistral-7B-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