Files
amd-r9700-ai-toolboxes/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__rocm-7-nightly__fa1__dual.log
T
Donato Capitella 3d9087c39b updated benchmarks
2025-11-30 13:47:32 +00:00

12 lines
811 B
Plaintext

ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | pp512 | 1544.19 ± 224.65 |
| qwen3moe 30B.A3B BF16 | 56.89 GiB | 30.53 B | ROCm | 99 | 1 | tg128 | 57.28 ± 0.07 |
build: fa0465954 (7205)