Donato Capitella
11 lines
736 B
Plaintext
11 lines
736 B
Plaintext
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 | mmap | test | t/s |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
|
|
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | pp512 | 275.91 ± 1.81 |
|
|
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 0 | tg128 | 11.91 ± 0.00 |
|
|
|
|
build: f1fbffb5 (6486)
|