Can't confirm with Y , llama download fails

App: Uncensored Local Studio (uncensored-local-studio.pinokio.git)
Repo: https://github.com/cocktailpeanut/uncensored-local-studio.pinokio.git
Generated: 2026-08-06T20:28:53.084Z
Pinokio: 8.0.40
Platform: linux x64
Node: v22.21.1

Summary

System

{
  "pinokio": {
    "version": "8.0.40",
    "node": "v22.21.1",
    "platform": "linux",
    "arch": "x64"
  },
  "hardware": {
    "gpu": "nvidia",
    "gpu_model": "nvidia geforce rtx 3060 ti",
    "ram_gb": 16,
    "vram_gb": 8
  },
  "os": {
    "platform": "linux",
    "distro": "cachyos",
    "release": "rolling",
    "kernel": "7.1.5-1-cachyos",
    "arch": "x64",
    "build": "rolling",
    "uefi": true
  },
  "system": {
    "manufacturer": "System manufacturer",
    "model": "System Product Name",
    "version": "System Version",
    "virtual": false
  },
  "cpu": {
    "manufacturer": "Intel",
    "brand": "Core™ i7-6700K",
    "vendor": "Intel",
    "family": "6",
    "model": "94",
    "stepping": "3",
    "speed": 4,
    "speedMin": 0.8,
    "speedMax": 4.2,
    "cores": 8,
    "physicalCores": 4,
    "processors": 1,
    "performanceCores": 4,
    "efficiencyCores": 0,
    "virtualization": true,
    "cache": {
      "l1d": 131072,
      "l1i": 131072,
      "l2": 1048576,
      "l3": 8388608
    }
  },
  "memory": {
    "total": 16698773504,
    "free": 207302656,
    "used": 16491470848,
    "active": 15293730816,
    "available": 1405042688,
    "buffers": 16384,
    "cached": 1694588928,
    "slab": 448008192,
    "buffcache": 2142613504,
    "swaptotal": 16698568704,
    "swapused": 9918517248,
    "swapfree": 6780051456
  },
  "gpus": [
    {
      "model": "nvidia geforce rtx 3060 ti"
    }
  ],
  "graphics": {
    "controllers": [
      {
        "vendor": "NVIDIA Corporation",
        "model": "NVIDIA GeForce RTX 3060 Ti",
        "bus": "Onboard",
        "vram": 7837,
        "vramDynamic": false,
        "driverVersion": "610.43.03"
      }
    ],
    "displays": [
      {
        "main": false,
        "builtin": false,
        "connection": "HDMI-A-1",
        "currentResX": 1920,
        "currentResY": 1080,
        "currentRefreshRate": 59
      },
      {
        "main": true,
        "builtin": false,
        "connection": "DP-2",
        "currentResX": 1920,
        "currentResY": 1080,
        "currentRefreshRate": 59
      }
    ]
  }
}

Logs

logs/api/install.js/1786047463217

Source: api / install.js
Lines: 43 total, last 43 included

[api shell.run]
<<PINOKIO_SHELL>>eval "$(conda shell.bash hook)" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base && bash scripts/setup/setup.sh

  ============================================================
   UNCENSORED AI STUDIO      -  Linux First-Time Setup
   100% Self-Contained  |  No System Install Required
  ============================================================

   OK   Linux runtime ABI ready: glibc 2.44, GLIBCXX_3.4.36
   OK   Linux OpenMP runtime ready: libgomp.so.1

  [1/7] Setting up portable Node.js (/home/wander/pinokio/api/uncensored-local-studio.pinokio.git/app/app/tools/node-linux/)
  ------------------------------------------------------------
   OK   Portable Node.js already ready: v22.12.0

  [2/7] Detecting GPU vendor: nvidia
  ------------------------------------------------------------
   OK   CPU backend already ready.
   OK   Vulkan backend already ready.

  ============================================================
   NVIDIA GPU Detected
  ============================================================
   To get the best performance, you can use the CUDA backend.
   Setting this up can download a prebuilt binary or compile from
   source (which takes 10-15 minutes).

   Alternatively, you can use the Vulkan backend which is already
   installed and runs immediately (recommended for GTX cards).
  ============================================================

   Do you want to proceed with CUDA setup? [y/N]:    >>   Declined CUDA setup. Using Vulkan GPU backend instead.

  [3/7] Setting up llama.cpp text backend
  ------------------------------------------------------------
   >>   Downloading llama-b9668-bin-ubuntu-cuda-12.4-x64.tar.gz
##O=-#     #                                                                                                                                                                        curl: (22) The requested URL returned error: 404

mv: cannot stat '/home/wander/pinokio/api/uncensored-local-studio.pinokio.git/app/app/tools/llama-b9668-bin-ubuntu-cuda-12.4-x64.tar.gz.part': No such file or directory
Error: Archive not found: /home/wander/pinokio/api/uncensored-local-studio.pinokio.git/app/app/tools/llama-b9668-bin-ubuntu-cuda-12.4-x64.tar.gz
   XX   llama-server was not found after extracting llama-b9668-bin-ubuntu-cuda-12.4-x64.tar.gz
   !!   Skipping optional llama.cpp backend for NVIDIA CUDA acceleration (llama-b9668-bin-ubuntu-cuda-12.4-x64.tar.gz)
   >>   Downloading llama-b9668-bin-ubuntu-sycl-fp32-x64.tar.gz