ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model                          |       size |     params | backend    | ngl | n_ubatch | fa | mmap |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0    | 106.65 GiB |   107.77 B | ROCm       |  99 |     2048 |  1 |    0 |           pp512 |       268.04 ± 46.82 |
| llama4 17Bx16E (Scout) Q8_0    | 106.65 GiB |   107.77 B | ROCm       |  99 |     2048 |  1 |    0 |           tg128 |         12.14 ± 0.00 |

build: 1c398dc9e (7034)