Updated benchmarks

This commit is contained in:
Donato Capitella
2025-09-17 10:41:14 +01:00
parent f4506ca711
commit 006aaa64e1
408 changed files with 14136 additions and 9467 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 | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 0 | pp512 | 646.07 ± 6.86 |
| gpt-oss ?B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 0 | tg128 | 45.50 ± 0.01 |
| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 0 | pp512 | 641.87 ± 3.27 |
| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 0 | tg128 | 47.17 ± 0.01 |
build: de219279 (6181)
build: f1fbffb5 (6486)