Files
amd-strix-halo-toolboxes/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm-7.2__hblt0__fa1__longctx32768.log
T
2026-01-23 15:11:13 +00:00

9 lines
689 B
Plaintext

ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | pp2048 @ d32768 | 28.46 ± 0.36 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | ROCm | 99 | 2048 | 1 | tg32 @ d32768 | 2.44 ± 0.04 |
build: a14b960bc (7816)