![[ICO]](/icons/blank.gif){kind=icon}
![[PARENTDIR]](/icons/back.gif){kind=icon}
![[TXT]](/icons/text.gif){kind=icon}
| Name | Last modified | Size | Description |
|---|---|---|---|---|
| Parent Directory | - | ||
| qwen_27b_iq4_16gb.sh | 2026-08-27 23:51 | 1.6K | |
| qwen_27b_q6_K_L_dual_gpu_28GB.sh | 2026-08-27 23:50 | 2.1K | |
| qwen_35b_a3b_moe_dual_gpu_28gb.sh | 2026-08-27 23:52 | 2.1K | |
Example scripts for llama-server, this are meant to show the usage and paramenters for the benchmarks, users should adapt -ub , --tensor-split and any other parameters that fit their system, yet the scripts here use --fit-target in order to obtain automatically the max context possible found by the auto fitter.