Llamacpp imatrix Quantizations of DeepScaleR 1.5B Preview by agentica org Using llama.cpp release b4671 for quantization. Original model: https://huggingface.co/agentica org/DeepScaleR 1.5B Preview All quants made using imatrix option with dataset from here Run them in LM Studio Run them directly with llama.cpp, or any other llama.cpp based project Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description DeepScaleR 1.5B Preview f32.gguf f32 7.11GB false Full F32 weights. DeepScaleR 1.5B Preview f16.gguf f16 3.56GB false Full F16 weights. DeepScaleR 1.5B Preview Q8 0.gguf Q8 0 1.89GB false Extremely high quality, generally unneeded but max available quant. DeepScaleR 1.5B Preview Q6 K L.gguf Q6 K L 1.58GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . DeepScaleR 1.5B Preview Q6 K.gguf Q6 K 1.46GB false Very high quality, near perfect, recommended . DeepScaleR 1.5B Preview Q5 K L.gguf Q5 K L 1.43GB false Uses Q8 0 for embed and output weights. High quality, recommended . DeepScaleR 1.5B Preview Q5 K M.gguf Q5 K M 1.29GB false High quality, recommended . DeepScaleR 1.5B Preview Q4 K L…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy