11 lines
803 B
Plaintext
11 lines
803 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: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
|
| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
|
|
| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 254.16 ± 0.00 |
|
|
| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 35.85 ± 0.00 |
|
|
|
|
build: 1c398dc9e (7034)
|