Files
amd-r9700-ai-toolboxes/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4-rocwmma__hblt0__fa1__single.log
T
Donato Capitella cef614d895 updated benchmarks
2025-12-06 09:24:07 +00:00

11 lines
733 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 AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | pp512 | 4694.36 ± 55.31 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | tg128 | 134.68 ± 0.47 |
build: 6016d0bd4 (7285)