Files
amd-strix-halo-toolboxes/benchmark/results/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003__vulkan_radv.log
T
Donato Capitella 765cc5c733 updated benchs
2025-10-12 07:39:42 +01:00

9 lines
745 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 | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | Vulkan | 99 | 0 | pp512 | 272.53 ± 1.82 |
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | Vulkan | 99 | 0 | tg128 | 12.58 ± 0.01 |
build: a3cb0474 (6735)