Files
amd-strix-halo-toolboxes/benchmark/results/gemma-4-26B-A4B-it-UD-Q8_K_XL__rocm7-nightlies__fa1__longctx32768.log
T
Donato Capitella 7aa6e6dea9 update benchmarks
2026-04-11 11:18:45 +01:00

9 lines
760 B
Plaintext

ggml_cuda_init: found 1 ROCm devices (Total VRAM: 126976 MiB):
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, VRAM: 126976 MiB
| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| gemma4 ?B Q8_0 | 25.94 GiB | 25.23 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 596.78 ± 7.98 |
| gemma4 ?B Q8_0 | 25.94 GiB | 25.23 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 33.35 ± 0.00 |
build: 3f8752b55 (8743)