FROM./bartowski/DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf
ollamacreatemy-deepseek-r1-32b-gguf-f.\deepseek-r1-32b.gguf
ollamarunmy-deepseek-r1-32b-gguf:latest
NAMEIDSIZEPROCESSORUNTILmy-deepseek-r1-32b-gguf:latestad9f11c41b7a25GB87%/13%CPU/GPU3minutesfromnow
https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#git-bash-mingw64
build/bin/Release/llama-cli-m"/path/to/DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf"-ngl100-c16384-t10-n-2-cnv
ggml_vulkan: Device memory allocation of size 1025355776 failed.ggml_vulkan: vk:evice::allocateMemory: ErrorOutOfDeviceMemoryllama_model_load: error loading model: unable to allocate Vulkan0 bufferllama_model_load_from_file_impl: failed to load modelcommon_init_from_params: failed to load model 'D:/llm/Model/bartowski/DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf'main: error: unable to load model
//GivenamodelandoneormoreGPUtargets,predicthowmanylayersandbyteswecanload,andthetotalsize//TheGPUsprovidedmustallbethesameLibraryfuncEstimateGPULayers(gpus[]discover.GpuInfo,f*ggml.GGML,projectors[]string,optsapi.Options)MemoryEstimate{//Graphsizeforapartialoffload,appliestoallGPUsvargraphPartialOffloaduint64//Graphsizewhenalllayersareoffloaded,appliestoallGPUsvargraphFullOffloaduint64//FinalgraphoffloadonceweknowfullorpartialvargraphOffloaduint64...| 欢迎光临 链载Ai (https://www.lianzai.com/) | Powered by Discuz! X3.5 |