Files
amd-strix-halo-toolboxes/benchmark/results/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__vulkan_radv__fa1.log
T
Donato Capitella 2d09b9e6db updated benchmarks
2026-02-05 19:03:13 +00:00

9 lines
738 B
Plaintext

ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Radeon 8060S Graphics (RADV GFX1151) (radv) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | Vulkan | 99 | 1 | pp512 | 99.39 ± 0.58 |
| llama 70B Q8_0 | 75.65 GiB | 70.55 B | Vulkan | 99 | 1 | tg128 | 2.76 ± 0.04 |
build: e0c93af2a (7938)