ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 2 CUDA devices: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes Device 1: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
| model | size | params | backend | ngl | test | t/s |
|---|---|---|---|---|---|---|
| seed_oss 36B Q4_K - Medium | 20.26 GiB | 36.15 B | CUDA | 35 | pp8 | 26.65 ± 0.22 |
| seed_oss 36B Q4_K - Medium | 20.26 GiB | 36.15 B | CUDA | 35 | tg128 | 4.84 ± 0.03 |
build: 92bb442ad (7040)