julian/amd-strix-halo-toolboxes
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

adding raw benchmark results

Browse Source
This commit is contained in:
Donato Capitella
2025-08-09 10:44:09 +01:00
parent 0dd1f8d047
commit 8972ef01ff
320 changed files with 3580 additions and 10779 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/results/llama3.3-70.6B-Q4_K_M__rocm7_beta.log
+3 -3
View File
@@ -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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama 70B Q4_K - Medium | 39.59 GiB | 70.55 B | ROCm | 99 | 0 | pp512 | 33.91 ± 0.04 |
| llama 70B Q4_K - Medium | 39.59 GiB | 70.55 B | ROCm | 99 | 0 | tg128 | 4.60 ± 0.00 |
| llama 70B Q4_K - Medium | 39.59 GiB | 70.55 B | ROCm | 999 | 0 | pp512 | 33.88 ± 0.02 |
| llama 70B Q4_K - Medium | 39.59 GiB | 70.55 B | ROCm | 999 | 0 | tg128 | 4.61 ± 0.00 |
build: 66625a59 (6040)
build: cd6983d5 (6119)