Modelpublic

bartowski/mistral-7b-v0.1-layla-v4-chatml-GGUF

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

2likes407downloads

Model Card

Llamacpp Quantizations of mistral-7b-v0.1-layla-v4-chatml

Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2405">b2405</a> for quantization.

Original model: https://huggingface.co/l3utterfly/mistral-7b-v0.1-layla-v4-chatml

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

Filename	Quant type	File Size	Description
mistral-7b-v0.1-layla-v4-chatml-Q8_0.gguf	Q8_0	7.69GB	Extremely high quality, generally unneeded but max available quant.
mistral-7b-v0.1-layla-v4-chatml-Q6_K.gguf	Q6_K	5.94GB	Very high quality, near perfect, recommended.
mistral-7b-v0.1-layla-v4-chatml-Q5_K_M.gguf	Q5KM	5.13GB	High quality, very usable.
mistral-7b-v0.1-layla-v4-chatml-Q5_K_S.gguf	Q5KS	4.99GB	High quality, very usable.
mistral-7b-v0.1-layla-v4-chatml-Q5_0.gguf	Q5_0	4.99GB	High quality, older format, generally not recommended.
mistral-7b-v0.1-layla-v4-chatml-Q4_K_M.gguf	Q4KM	4.36GB	Good quality, similar to 4.25 bpw.
mistral-7b-v0.1-layla-v4-chatml-Q4_K_S.gguf	Q4KS	4.14GB	Slightly lower quality with small space savings.
mistral-7b-v0.1-layla-v4-chatml-Q4_0.gguf	Q4_0	4.10GB	Decent quality, older format, generally not recommended.
mistral-7b-v0.1-layla-v4-chatml-Q3_K_L.gguf	Q3KL	3.82GB	Lower quality but usable, good for low RAM availability.
mistral-7b-v0.1-layla-v4-chatml-Q3_K_M.gguf	Q3KM	3.51GB	Even lower quality.
mistral-7b-v0.1-layla-v4-chatml-Q3_K_S.gguf	Q3KS	3.16GB	Low quality, not recommended.
mistral-7b-v0.1-layla-v4-chatml-Q2_K.gguf	Q2_K	2.71GB	Extremely low quality, not recommended.

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