RefalMachine

/

RuadaptQwen3-4B-Instruct-GGUF

like 5

└─$ ~/WORK/llama.cpp/build_blas//bin/llama-cli -mli -m ~/WORK/model_LLM/RuadaptQwen3-4B-Instruct_Q4_K_M.gguf

Loading model... /ggml_aligned_malloc: insufficient memory (attempted to allocate 36864.00 MB)
ggml_backend_cpu_buffer_type_alloc_buffer: failed to allocate buffer of size 38654705664
alloc_tensor_range: failed to allocate CPU buffer of size 38654705664
llama_init_from_model: failed to initialize the context: failed to allocate buffer for kv cache
zsh: segmentation fault ~/WORK/llama.cpp/build_blas//bin/llama-cli -mli -m

└─$ ~/WORK/llama.cpp/build_blas//bin/llama-cli --version
version: 7783 (d1e355648)
built with GNU 15.2.0 for Linux x86_64