Quantization made by Richard Erkhov. Github Discord Request more models gemma 7b it GGUF Model creator: https://huggingface.co/google/ Original model: https://huggingface.co/google/gemma 7b it/ Name Quant method Size gemma 7b it.Q2 K.gguf Q2 K 3.24GB gemma 7b it.IQ3 XS.gguf IQ3 XS 3.54GB gemma 7b it.IQ3 S.gguf IQ3 S 3.71GB gemma 7b it.Q3 K S.gguf Q3 K S 3.71GB gemma 7b it.IQ3 M.gguf IQ3 M 3.82GB gemma 7b it.Q3 K.gguf Q3 K 4.07GB gemma 7b it.Q3 K M.gguf Q3 K M 4.07GB gemma 7b it.Q3 K L.gguf Q3 K L 4.39GB gemma 7b it.IQ4 XS.gguf IQ4 XS 4.48GB gemma 7b it.Q4 0.gguf Q4 0 4.67GB gemma 7b it.IQ4 NL.gguf IQ4 NL 4.69GB gemma 7b it.Q4 K S.gguf Q4 K S 4.7GB gemma 7b it.Q4 K.gguf Q4 K 4.96GB gemma 7b it.Q4 K M.gguf Q4 K M 4.96GB gemma 7b it.Q4 1.gguf Q4 1 5.12GB gemma 7b it.Q5 0.gguf Q5 0 5.57GB gemma 7b it.Q5 K S.gguf Q5 K S 5.57GB gemma 7b it.Q5 K.gguf Q5 K 5.72GB gemma 7b it.Q5 K M.gguf Q5 K M 5.72GB gemma 7b it.Q5 1.gguf Q5 1 6.02GB gemma 7b it.Q6 K.gguf Q6 K 6.53GB Original model description: library name: transformers tags: [] widget: messages: role: user content: How does the brain work? inference: parameters: max new tokens: 200 extra gated heading: Access Gemma on Hugging Face extra…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy