gguf unable load

[bambooqj]

.........................................................................................
llama_new_context_with_model: n_ctx = 65536
llama_new_context_with_model: n_batch = 512
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: freq_base = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA_Host KV buffer size = 8192.00 MiB
llama_new_context_with_model: KV self size = 8192.00 MiB, K (f16): 4096.00 MiB, V (f16): 4096.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.50 MiB
ggml_backend_cuda_buffer_type_alloc_buffer: allocating 4507.00 MiB on device 0: cudaMalloc failed: out of memory
ggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 4725934080
llama_new_context_with_model: failed to allocate compute buffers
llama_init_from_gpt_params: error: failed to create context with model 'C:\Users\Administrator.ollama\models\blobs\sha256-912687f2b75ca31331bfcf8b55a34a366dbb0f31df6bf65bc464c1d2431b92be'
{"function":"load_model","level":"ERR","line":410,"model":"C:\Users\Administrator\.ollama\models\blobs\sha256-912687f2b75ca31331bfcf8b55a34a366dbb0f31df6bf65bc464c1d2431b92be","msg":"unable to load model","tid":"11992","timestamp":1715077029}

---

https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-64k-GGUF/tree/main