https://onnocenter.or.id/wiki/index.php?action=history&feed=atom&title=LMStudio%3A_Ubuntu_26.04_NVIDIA_Install 2026-06-28T00:29:51Z Revision history for this page on the wiki MediaWiki 1.35.4 https://onnocenter.or.id/wiki/index.php?title=LMStudio:_Ubuntu_26.04_NVIDIA_Install&diff=73669&oldid=prev 2026-06-27T21:01:39Z

<p><span dir="auto"><span class="autocomment">= Untuk AI lokal / LM Studio / Ollama</span></span></p> <table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 21:01, 27 June 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l71" >Line 71:</td> <td colspan="2" class="diff-lineno">Line 71:</td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Alternatifnya gunakan proses MOK enrollment, tapi untuk lab lokal biasanya disable Secure Boot lebih sederhana.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Alternatifnya gunakan proses MOK enrollment, tapi untuk lab lokal biasanya disable Secure Boot lebih sederhana.</div></td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>== Untuk AI lokal / LM Studio / Ollama=</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>== Untuk AI lokal / LM Studio / Ollama<ins class="diffchange diffchange-inline">=</ins>=</div></td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Driver saja cukup dulu. CUDA toolkit tidak wajib untuk Ollama/LM Studio, karena yang penting GPU NVIDIA terbaca oleh driver.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Driver saja cukup dulu. CUDA toolkit tidak wajib untuk Ollama/LM Studio, karena yang penting GPU NVIDIA terbaca oleh driver.</div></td></tr> </table>

Onnowpurbo https://onnocenter.or.id/wiki/index.php?title=LMStudio:_Ubuntu_26.04_NVIDIA_Install&diff=73668&oldid=prev 2026-06-27T20:55:13Z

<p>Created page with &quot;= Install NVIDIA Driver di Ubuntu 26.04 Desktop= == 1. Cek GPU== lspci | grep -Ei &quot;vga|3d|display|nvidia&quot; == 2. Update sistem== sudo apt update sudo apt upgrade -y sud...&quot;</p> <p><b>New page</b></p><div>= Install NVIDIA Driver di Ubuntu 26.04 Desktop=<br /> <br /> == 1. Cek GPU==<br /> <br /> lspci | grep -Ei &quot;vga|3d|display|nvidia&quot;<br /> <br /> == 2. Update sistem==<br /> <br /> sudo apt update<br /> sudo apt upgrade -y<br /> sudo apt install linux-headers-$(uname -r) ubuntu-drivers-common -y<br /> <br /> == 3. Cek driver yang direkomendasikan Ubuntu==<br /> <br /> ubuntu-drivers devices<br /> <br /> Cari baris seperti:<br /> <br /> driver : nvidia-driver-XXX - recommended<br /> <br /> == 4. Install otomatis driver rekomendasi==<br /> <br /> Cara paling aman:<br /> <br /> sudo ubuntu-drivers install<br /> <br /> Atau:<br /> <br /> sudo ubuntu-drivers autoinstall<br /> <br /> Ubuntu dan NVIDIA sama-sama merekomendasikan jalur paket/APT untuk instalasi driver, bukan installer `.run` manual. ([Ubuntu][1])<br /> <br /> == 5. Reboot==<br /> <br /> sudo reboot<br /> <br /> == 6. Cek setelah reboot==<br /> <br /> nvidia-smi<br /> <br /> Jika muncul tabel NVIDIA, berarti driver sudah aktif.<br /> <br /> Cek module:<br /> <br /> lsmod | grep nvidia<br /> <br /> Cek render:<br /> <br /> glxinfo | grep &quot;OpenGL renderer&quot;<br /> <br /> Kalau `glxinfo` belum ada:<br /> <br /> sudo apt install mesa-utils -y<br /> <br /> == Jika Secure Boot aktif dan driver tidak jalan==<br /> <br /> Cek:<br /> <br /> mokutil --sb-state<br /> <br /> Kalau `SecureBoot enabled`, paling mudah untuk lab AI lokal:<br /> <br /> # Masuk BIOS/UEFI<br /> # Disable Secure Boot<br /> # Boot Ubuntu lagi<br /> # Jalankan:<br /> <br /> sudo apt reinstall nvidia-driver-$(nvidia-smi --query-gpu=driver_version --format=csv,noheader | cut -d. -f1) -y<br /> sudo reboot<br /> <br /> Alternatifnya gunakan proses MOK enrollment, tapi untuk lab lokal biasanya disable Secure Boot lebih sederhana.<br /> <br /> == Untuk AI lokal / LM Studio / Ollama=<br /> <br /> Driver saja cukup dulu. CUDA toolkit tidak wajib untuk Ollama/LM Studio, karena yang penting GPU NVIDIA terbaca oleh driver.<br /> <br /> Cek:<br /> <br /> nvidia-smi<br /> <br /> Lalu test Ollama:<br /> <br /> ollama run qwen3:4b<br /> <br /> Saat model jalan:<br /> <br /> watch -n1 nvidia-smi<br /> <br /> Kalau VRAM naik, berarti GPU dipakai.<br /> <br /> [1]: https://ubuntu.com/server/docs/how-to/graphics/install-nvidia-drivers/?utm_source=chatgpt.com &quot;NVIDIA drivers installation - Ubuntu Server documentation&quot;</div>

Onnowpurbo