Files
amd-strix-halo-toolboxes/benchmark/results/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M__vulkan_radv__fa1__longctx16384.log
T
Donato Capitella 2c8a1e2eef updated benchmarks
2025-12-21 18:49:08 +00:00

9 lines
766 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 | mmap | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | Vulkan | 99 | 1 | 0 | pp2048 @ d16384 | 168.69 ± 0.00 |
| qwen3moe 30B.A3B Q4_K - Medium | 17.35 GiB | 30.53 B | Vulkan | 99 | 1 | 0 | tg32 @ d16384 | 47.63 ± 0.00 |
build: 2aa45ef9e (7423)