Frank
d82c5c03b7
One quant step down from Q6_K on the same CUDA build and the same shape: 2 x 262,144 with K f16 + V q8_0. The 0.86 GiB freed from the weights is headroom, not a new window — the native 262,144 cap is already reached, and f16 V would still cost 3.96 GiB more than the pool can carry.
20 lines
628 B
Desktop File
20 lines
628 B
Desktop File
[Unit]
|
|
Description=llama.cpp MiMo-V2.6-Distill-Qwen-9B Q5_K_M GGUF (qwen35 hybrid, 2x262144, f16 K + q8_0 V) on the RTX 3090 (dankclaw, frank-small)
|
|
After=network-online.target
|
|
Wants=network-online.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=dank
|
|
Group=dank
|
|
# CUDA pins its staging buffers, so the process needs the memlock budget even
|
|
# though the weights themselves are copied into VRAM.
|
|
LimitMEMLOCK=infinity
|
|
Environment="FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-small.env"
|
|
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-small.sh
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|