how to enable "has tensor"

[codrut-popescu]

I a running macOS arm64 with an M4 Max CPU
I am trying to compile it

cd llama.cpp-b6969
cmake -B build -DGGML_METAL=ON
cmake --build build --config Release -j 8

But the result does not support tensors

./llama-cli --version
ggml_metal_device_init: tensor API disabled for pre-M5 device
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 4.869 sec
ggml_metal_device_init: GPU name: Apple M4 Max
ggml_metal_device_init: GPU family: MTLGPUFamilyApple9 (1009)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal4 (5002)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 115448.73 MB
version: 0 (unknown)
built with Apple clang version 17.0.0 (clang-1700.4.4.1) for arm64-apple-darwin25.1.0

Also, what does "tensor API disabled for pre-M5 device"? Why? Does it not work for M4 Max?

I am beginner

[codrut-popescu]

Nevermind, I have asked a wrong question. M4 doesn't have GPU tensors so of course they are disabled.