Files
amd-strix-halo-toolboxes/benchmark/results/gpt-oss-20b-mxfp4__rocm6_4_4__hblt0__fa1__longctx32768.log
T
Donato Capitella a7ace8dba7 updted benchmarks
2026-03-30 08:37:15 +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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 730.49 ± 1.20 |
| gpt-oss 20B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d32768 | 56.89 ± 0.05 |
build: 2405d59cb (8577)