Files
amd-strix-halo-toolboxes/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__vulkan_amdvlk.log
T
Donato Capitella 006aaa64e1 Updated benchmarks
2025-09-17 10:41:14 +01:00

9 lines
748 B
Plaintext

ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | Vulkan | 99 | 0 | pp512 | 97.72 ± 0.36 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | Vulkan | 99 | 0 | tg128 | 2.81 ± 0.00 |
build: f1fbffb5 (6486)