Files
amd-r9700-ai-toolboxes/benchmark/results/gemma-3-4b-it-Q3_K_S__rocm-7.9__fa1__longctx32768__single.log
Donato Capitella 2e8bef127f benchmakr updates
2025-12-17 08:01:12 +00:00

11 lines
773 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, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 2489.46 ± 0.00 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 99.14 ± 0.00 |
build: 2aa45ef9e (7423)