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
@@ -0,0 +1,10 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | pp512 | 326.80 ± 4.56 |
| gpt-oss ?B BF16 | 38.97 GiB | 20.91 B | ROCm | 99 | 0 | tg128 | 27.13 ± 0.01 |
build: 1fe00296 (6182)