DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to test the experimental RTX 4070 Ti SUPER or 4060 Ti path with GPU Unlock Ada

Opt in to the experimental AD103 or AD106 target with its flag and one exact PCI address.

Short answer: Install with make install as for the RTX 4090; then For an RTX 4070 Ti SUPER, add gpu_unlock.targets=0000:01:00.0 gpu_unlock.ad103_experimental=1 with your own address; For an RTX 4060 Ti 16GB, add gpu_unlock.targets=0000:01:00.0 gpu_unlock.ad106_experimental=1 with your own address. All steps.

Reverse engineering. The unlock runs a payload derived from published analysis of NVIDIA's debug booter and changes GPU register state from a kernel module before the driver loads. It is unofficial, unsupported by NVIDIA, may void your warranty, and has been validated on very few cards.

Who it is forAn RTX 4070 Ti SUPER or RTX 4060 Ti 16GB owner willing to be an early tester on Linux.

The problemOnly one card of each model has been validated, so the module never selects them by default.

The outcomeA tested unlock on your exact card, or a clean refusal in the kernel log.

What you need first

  • A Linux machine you fully control, with a spare stock boot entry to fall back to
  • RTX 4090 (10de:2684); RTX 4070 Ti SUPER (10de:2705) and RTX 4060 Ti 16GB (10de:2805) are experimental and validated on one card each
  • Kernel headers and a working DKMS toolchain, with CONFIG_CRYPTO_LIB_SHA256 in the kernel
  • The stock NVIDIA driver
  • Secure Boot turned off, or the out-of-tree module signed with your own key
  • Your own stock benchmark numbers taken before you enable it

Steps

  1. Install with make install as for the RTX 4090
  2. For an RTX 4070 Ti SUPER, add gpu_unlock.targets=0000:01:00.0 gpu_unlock.ad103_experimental=1 with your own address
  3. For an RTX 4060 Ti 16GB, add gpu_unlock.targets=0000:01:00.0 gpu_unlock.ad106_experimental=1 with your own address
  4. Power the machine off and start it again
  5. Run journalctl -k -b | grep gpu_unlock and remove gpu_unlock.targets= from the kernel command line to disable it

Prompt for your agent

Install JustAResearcher/gpu-unlock-ada and enable the experimental path for my <RTX 4070 Ti SUPER or RTX 4060 Ti 16GB> at <PCI address> with its experimental flag, keeping a stock boot entry. After a cold boot, report the gpu_unlock kernel log lines and whether the card unlocked.

Caveat. targets=all never selects these cards, other Ada models are not accepted, and shared firmware does not mean an untested card will work.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for JustAResearcher/gpu-unlock-ada and "Test the experimental RTX 4070 Ti SUPER or 4060 Ti path"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer