# Gemini-cli, zeroclaw, Llama.cpp, Qwen3.5 on TK1 **URL:** \ **Category:** Jetson TK1\ **Tags:** llama\ **Created:** [April 5, 2026, 12:58pm UTC](https://forums.developer.nvidia.com/t/gemini-cli-zeroclaw-llama-cpp-qwen3-5-on-tk1/365653 "2026-04-05T12:58:41Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![i6mods](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/i6mods/32/33063_2.png) [@i6mods](https://forums.developer.nvidia.com/u/i6mods)\ **Post date:** [April 5, 2026, 12:58pm UTC](https://forums.developer.nvidia.com/t/gemini-cli-zeroclaw-llama-cpp-qwen3-5-on-tk1/365653/1 "2026-04-05T12:58:41Z")
I have a TK1 running llama.cpp if anyone has a dgx spark they would like to give to me i will be forever grateful. to get llama.cpp running: Have a TK1 with Grinch kernel (so i can use wifi) installed debian11 32-bit armv7 to TK1 (onto sata drive) boot debian install llama.cpp wget llm model run model Issues i had: ubuntu 14.04 could not compile llama.cpp ubuntu 18 is possible to install but is quite bloated (2gb ram limit + 16gb emmc) but again could not install llama.cpp due to cmake versions and a few other outdated things. debian11 install was just a few hundred MB debian 11 uses just 52MB RAM giving almost all 1.7GB ram free for llama other issues: My TK1 was brick due to HDMI hardware failure & wifi not configured so no direct ssh session possible connected db9 serial debug with minicom fresh install ubuntu 14.04 with cuda (grinch for pcie wifi) connected old sata drive to TK1 sata port installed debian11 to sata ssd enabled boot option grinch or debian Wish i had cuda gpu, but only functioning on grinch 14.04 Was so much fun to achieve this as a personal challenge, thank you. ![Screenshot 2026-04-05 at 13.29.21](https://global.discourse-cdn.com/nvidia/original/4X/a/a/c/aac6ce1eaab5261b44d9f6c9077eb589405bd03e.png) ![2](https://global.discourse-cdn.com/nvidia/original/4X/9/2/e/92e09d35f0034a863dfba771b0d6b0ebdc7d89de.jpeg) ---
**Author:** ![kayccc](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/kayccc/32/14043_2.png) [@kayccc](https://forums.developer.nvidia.com/u/kayccc)\ **Post date:** [April 6, 2026, 11:56pm UTC](https://forums.developer.nvidia.com/t/gemini-cli-zeroclaw-llama-cpp-qwen3-5-on-tk1/365653/2 "2026-04-06T23:56:25Z")
Thanks for your sharing to the community. ---
**Author:** ![i6mods](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/i6mods/32/33063_2.png) [@i6mods](https://forums.developer.nvidia.com/u/i6mods)\ **Post date:** [April 7, 2026, 5:23am UTC](https://forums.developer.nvidia.com/t/gemini-cli-zeroclaw-llama-cpp-qwen3-5-on-tk1/365653/3 "2026-04-07T05:23:20Z")
further to compiling llama.cpp for tk1, today compiled zeroclaw, only around five hours to complete ![Screenshot 2026-04-07 at 06.20.24](https://global.discourse-cdn.com/nvidia/original/4X/1/5/8/15858402e402833fe1d2af7bfecd28dbf328d49c.jpeg) ![Screenshot 2026-04-07 at 08.01.31](https://global.discourse-cdn.com/nvidia/original/4X/1/c/3/1c376feae8f42a89eb73e63841322ccefa946599.png) ---
**Author:** ![i6mods](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/i6mods/32/33063_2.png) [@i6mods](https://forums.developer.nvidia.com/u/i6mods)\ **Post date:** [April 7, 2026, 5:37am UTC](https://forums.developer.nvidia.com/t/gemini-cli-zeroclaw-llama-cpp-qwen3-5-on-tk1/365653/4 "2026-04-07T05:37:34Z")
and also gemini cli installed cleanly after installing node latest for armv7: ![Screenshot 2026-04-07 at 06.35.59](https://global.discourse-cdn.com/nvidia/original/4X/3/9/1/391e5754c82a8e6f4a6d4e3f19e4378595a3bf25.jpeg) cpu and mem use is v smoll, runs nicely ![Screenshot 2026-04-07 at 06.41.47](https://global.discourse-cdn.com/nvidia/original/4X/3/7/c/37cd64a76d841f6bc8444f16e0b5c46ec21304ea.png) ![Screenshot 2026-04-07 at 06.45.35](https://global.discourse-cdn.com/nvidia/original/4X/1/8/b/18ba7ddc4de2a1d77f8c2d4ed96c964182469a42.jpeg)