Updated benchmarks

This commit is contained in:
Donato Capitella
2025-08-17 08:53:16 +01:00
parent b72bbd64f8
commit 62e5080102
657 changed files with 12622 additions and 16283 deletions
@@ -4,7 +4,7 @@ ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 999 | 1 | 0 | pp512 | 1474.70 ± 11.50 |
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 999 | 1 | 0 | tg128 | 63.31 ± 0.01 |
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | pp512 | 1460.58 ± 11.92 |
| gpt-oss ?B MXFP4 MoE | 11.27 GiB | 20.91 B | ROCm | 99 | 1 | 0 | tg128 | 64.26 ± 0.00 |
build: 34c9d765 (6122)
build: de219279 (6181)