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 | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 999 | 0 | pp512 | 1812.27 ± 4.63 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 999 | 0 | tg128 | 76.22 ± 0.01 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | pp512 | 2027.41 ± 4.62 |
| gemma3 4B Q3_K - Small | 1.80 GiB | 3.88 B | ROCm | 99 | 0 | tg128 | 77.12 ± 0.03 |
build: 79c1160b (6123)
build: de219279 (6181)