Files
amd-strix-halo-toolboxes/benchmark/results/Qwen3-30B-A3B-Instruct-2507-UD-Q6_K_XL__rocm-7alpha__fa1__longctx16384.log
T
Donato Capitella 2c8a1e2eef updated benchmarks
2025-12-21 18:49:08 +00:00

11 lines
803 B
Plaintext

ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d16384 | 273.12 ± 0.00 |
| qwen3moe 30B.A3B Q6_K | 24.53 GiB | 30.53 B | ROCm | 99 | 2048 | 1 | 0 | tg32 @ d16384 | 40.25 ± 0.00 |
build: 2aa45ef9e (7423)