Files
amd-r9700-ai-toolboxes/benchmark/results/Ministral-3-14B-Instruct-2512-BF16__rocm7.1.1__fa1__longctx32768__single.log
T
Donato Capitella 2e8bef127f benchmakr updates
2025-12-17 08:01:12 +00:00

11 lines
777 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 | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 447.71 ± 0.00 |
| mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 18.69 ± 0.00 |
build: 2aa45ef9e (7423)