Model ggml-large-v3.bin crashes with ggml_backend_cpu_buffer_type_alloc_buffer error

[DimucaTheDev]

Using model ggml-large-v3.bin.
Full command:
./whisper-cli "C:\ ... \Avicii - Hey Brother.mp3" -t 16 -m .\models\ggml-large-v3.bin

Full Log:

whisper_init_from_file_with_params_no_state: loading model from '.\models\ggml-large-v3.bin'
whisper_init_with_params_no_state: use gpu    = 1
whisper_init_with_params_no_state: flash attn = 1
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw        = 0
whisper_init_with_params_no_state: devices    = 1
whisper_init_with_params_no_state: backends   = 1
whisper_model_load: loading model
whisper_model_load: n_vocab       = 51866
whisper_model_load: n_audio_ctx   = 1500
whisper_model_load: n_audio_state = 1280
whisper_model_load: n_audio_head  = 20
whisper_model_load: n_audio_layer = 32
whisper_model_load: n_text_ctx    = 448
whisper_model_load: n_text_state  = 1280
whisper_model_load: n_text_head   = 20
whisper_model_load: n_text_layer  = 32
whisper_model_load: n_mels        = 128
whisper_model_load: ftype         = 1
whisper_model_load: qntvr         = 0
whisper_model_load: type          = 5 (large v3)
whisper_model_load: adding 1609 extra tokens
whisper_model_load: n_langs       = 100
ggml_backend_cpu_buffer_type_alloc_buffer: failed to allocate buffer of size 3094359040
alloc_tensor_range: failed to allocate CPU buffer of size 3094359040
D:\a\whisper.cpp\whisper.cpp\ggml\src\ggml-backend.cpp:189: GGML_ASSERT(buffer) failed

Environment:

• Windows 11 Pro 26100
• Ryzen 7 5700X 4.6GHz
• 64 GB Ram (see pic)
• Bins downloaded from Release page v1.8.2

Note that other model (base, tiny) work fine. Tried running with admin rights, but nothing changed