overclocking5060ti

A developer published a headless GPU overclocking and power-tuning method for Linux that relies purely on NVML, avoiding X11/Xorg and nvidia-settings. Tested on an RTX 5060 Ti 16GB running MoE inference with Strata, the setup applied a +5300 MHz memory offset, +450 MHz GPC offset and a 182W power limit via a systemd service, reaching roughly 108–118 tok/s with an 85.1% expert cache hit rate.

Pure-NVML, completely headless GPU overclocking and power tuning for Linux without any X11/Xorg or nvidia-settings display server hacks. Tested on RTX 5060 Ti 16GB hitting ~108–118 tok/s in MoE inference using Strata https://github.com/Niko1221/Strata by @coldniko https://x.com/coldniko . - Model Context: 30,000 tokens thinking budget capped at 22,500 - Reasoning / Thinking: 66 → 91.5 tok/s - Tool Calling / Generation: 107.9 tok/s sustained 1996 tokens in 19s - Expert Cache Hit Rate: 85.1% only 1.4% routed over PCIe - Memory OC: +5300 MHz via nvmlDeviceSetMemClkVfOffset - Core GPC OC: +450 MHz via nvmlDeviceSetGpcClkVfOffset - Power Limit: 182W Persistence mode ON Run the following bash script with sudo to set up the isolated Python venv, deploy all config files, and enable the systemd service: js /usr/bin/env bash set -euo pipefail echo "== 1. Setting up Python venv with nvidia-ml-py..." mkdir -p /opt/nvidia-nvml python3 -m venv /opt/nvidia-nvml /opt/nvidia-nvml/bin/pip install --upgrade pip /opt/nvidia-nvml/bin/pip install nvidia-ml-py echo "== 2. Creating /etc/default/nvidia-llama-power..." cat << 'EOF' /etc/default/nvidia-llama-power POWER LIMIT=182 MEMORY OFFSET=5300 GRAPHICS OFFSET=450 EOF echo "== 3. Creating /usr/local/sbin/nvidia-llama-oc.py..." cat << 'EOF' /usr/local/sbin/nvidia-llama-oc.py import os from pynvml import memory = int os.environ "MEMORY OFFSET" graphics = int os.environ "GRAPHICS OFFSET" nvmlInit try: h = nvmlDeviceGetHandleByIndex 0 nvmlDeviceSetMemClkVfOffset h, memory nvmlDeviceSetGpcClkVfOffset h, graphics mem actual = nvmlDeviceGetMemClkVfOffset h gpc actual = nvmlDeviceGetGpcClkVfOffset h if mem actual = memory: raise RuntimeError f"memory offset mismatch: requested={memory}, actual={mem actual}" if gpc actual = graphics: raise RuntimeError f"GPC offset mismatch: requested={graphics}, actual={gpc actual}" print f"memory offset: {mem actual} MHz" print f"GPC offset: {gpc actual} MHz" finally: nvmlShutdown EOF chmod +x /usr/local/sbin/nvidia-llama-oc.py echo "== 4. Creating /usr/local/sbin/nvidia-llama-power.sh..." cat << 'EOF' /usr/local/sbin/nvidia-llama-power.sh /bin/bash set -e source /etc/default/nvidia-llama-power export POWER LIMIT MEMORY OFFSET GRAPHICS OFFSET /usr/bin/nvidia-smi -pm 1 /usr/bin/nvidia-smi -pl "$POWER LIMIT" /usr/bin/nvidia-smi -rgc exec /opt/nvidia-nvml/bin/python /usr/local/sbin/nvidia-llama-oc.py EOF chmod +x /usr/local/sbin/nvidia-llama-power.sh echo "== 5. Creating /etc/systemd/system/nvidia-llama-power.service..." cat << 'EOF' /etc/systemd/system/nvidia-llama-power.service Unit Description=Set NVIDIA GPU profile for llama.cpp / Strata After=multi-user.target ConditionPathExists=/usr/bin/nvidia-smi Service Type=oneshot ExecStart=/usr/local/sbin/nvidia-llama-power.sh RemainAfterExit=yes Install WantedBy=multi-user.target EOF echo "== 6. Enabling and starting systemd service..." systemctl daemon-reload systemctl enable --now nvidia-llama-power.service echo "== All done Check status with: systemctl status nvidia-llama-power.service" Check service status: systemctl status nvidia-llama-power.service Expected output: ● nvidia-llama-power.service - Set NVIDIA GPU profile for llama.cpp / Strata Loaded: loaded /etc/systemd/system/nvidia-llama-power.service; enabled; preset: enabled Active: active exited ... nvidia-llama-power.sh: Enabled persistence mode via daemon for GPU 00000000:23:00.0. nvidia-llama-power.sh: Power limit for GPU 00000000:23:00.0 was set to 182.00 W from 180.00 W. nvidia-llama-power.sh: memory offset: 5300 MHz nvidia-llama-power.sh: GPC offset: 450 MHz To change power limit or clock offsets, simply edit /etc/default/nvidia-llama-power : sudo nano /etc/default/nvidia-llama-power And re-apply immediately: sudo systemctl restart nvidia-llama-power.service