ggml_cuda_init: found 1 CUDA devices (Total VRAM: 15866 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15866 MiB | model | size | params | backend | ngl | fa | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | --: | --------------: | -------------------: | | qwen35 27B PTQ1_0 - 1.75 bpw ternary (group 128) | 6.81 GiB | 28.59 B | CUDA | 99 | 1 | pp512 | 462.45 ± 4.56 | | qwen35 27B PTQ1_0 - 1.75 bpw ternary (group 128) | 6.81 GiB | 28.59 B | CUDA | 99 | 1 | pp4096 | 460.85 ± 0.71 | | qwen35 27B PTQ1_0 - 1.75 bpw ternary (group 128) | 6.81 GiB | 28.59 B | CUDA | 99 | 1 | tg128 | 56.07 ± 0.13 | build: f0e7f7a (9)