Tuxedo 17 (en Ubuntu 24) + GIGABYTE AORUS RTX 5060 Ti AI Box Carte Graphique - 16GB GDDR7.
-
Test :
sudo nvidia-smi -pm ENABLED;
sudo nvidia-smi -lgc 1000,2000;[ 586.874754] [drm] Initialized nvidia-drm 0.0.0 for 0000:05:00.0 on minor 0 [ 586.875976] nvidia 0000:05:00.0: [drm] Cannot find any crtc or sizes [ 586.875994] pci 0000:05:00.1: extending delay after power-on from D3hot to 20 msec [ 586.876033] pci 0000:05:00.1: D0 power state depends on 0000:05:00.0 [ 586.876184] snd_hda_intel 0000:05:00.1: enabling device (0000 -> 0002) [ 586.876324] snd_hda_intel 0000:05:00.1: Disabling MSI [ 586.876335] snd_hda_intel 0000:05:00.1: Handle vga_switcheroo audio client [ 586.876368] snd_hda_intel 0000:05:00.1: number of I/O streams is 30, forcing separate stream tags [ 586.977742] hdaudio hdaudioC2D0: no AFG or MFG node found [ 586.977758] hdaudio hdaudioC2D1: no AFG or MFG node found [ 586.977769] hdaudio hdaudioC2D2: no AFG or MFG node found [ 586.977780] hdaudio hdaudioC2D3: no AFG or MFG node found [ 586.977790] hdaudio hdaudioC2D4: no AFG or MFG node found [ 586.977800] hdaudio hdaudioC2D5: no AFG or MFG node found [ 586.977810] hdaudio hdaudioC2D6: no AFG or MFG node found [ 586.977820] hdaudio hdaudioC2D7: no AFG or MFG node found [ 586.977822] snd_hda_intel 0000:05:00.1: no codecs initialized [ 586.977847] snd_hda_intel 0000:05:00.1: GPU sound probed, but not operational: please add a quirk to driver_denylist [ 644.756905] NVRM: GPU at PCI:0000:05:00: GPU-5d8d2eb1-648d-e52f-369a-26f078362f02 [ 644.756912] NVRM: GPU Board Serial Number: 0 [ 644.756913] NVRM: Xid (PCI:0000:05:00): 79, GPU has fallen off the bus. [ 644.756920] NVRM: GPU 0000:05:00.0: GPU has fallen off the bus. [ 644.756922] NVRM: GPU 0000:05:00.0: GPU serial number is 0. [ 644.756929] NVRM: krcRcAndNotifyAllChannels_IMPL: RC all channels for critical error 79. [ 644.756948] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756961] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756966] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756970] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756973] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756977] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756981] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756985] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756988] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756993] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.756998] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757003] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757011] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757018] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757021] pcieport 0000:04:03.0: Unable to change power state from D3hot to D0, device inaccessible [ 644.757022] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757026] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757028] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757031] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757035] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757039] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757043] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757046] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757049] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757053] NVRM: _threadNodeCheckTimeout: API_GPU_ATTACHED_SANITY_CHECK failed! [ 644.757058] NVRM: prbEncStartAlloc: Can't allocate memory for protocol buffers. [ 644.757060] NVRM: A GPU crash dump has been created. If possible, please run NVRM: nvidia-bug-report.sh as root to collect this data before NVRM: the NVIDIA kernel module is unloaded. [ 644.757269] pcieport 0000:00:07.0: pciehp: Slot(0): Link Down -
As per Xid errors list (check PDF), the error 79 (GPU has fallen off the bus) can be related to variety of things such as driver or hardware issue, system memory corruption, bus error or thermal issue (overheating).
Run NVIDIA X Server Settings app (which comes with the drivers) and check the temperature, graphic clock, performance levels and GPU utilization levels.
The following post (based on this original thread), suggests to disable PCI-E ASPM (Active State Power Management) by changing boot params to pcie_aspm=off (it forcibly disables PCIe ASPM).
Related bug report: GPU has fallen off the bus.
Other reasons for ‘GPU has fallen off the bus’ errors
System overheating. Suggestions: Check temperature by nvidia-smi or use NVIDIA Settings GUI app. Alternatively use sensors command (install: sudo apt install lm-sensors && sudo sensors-detect) or psensor GUI app. PSU (Power Supply Unit) wattage doesn't meet requirements of your card(s). Suggestions: Check power usage by nvidia-smi command. To monitor usage in real-time, run: watch -n10 nvidia-smi. Consider reducing GPU/CPU load. Driver issues (unstable or due to bugs). Suggestions: Update nvidia drivers. The easiest way is to install latest CUDA libraries to avoid mismatch, e.g. sudo apt upgrade cuda-12-8. Check GPU errors (e.g. look for stack traces) in more details via less /var/log/kern.log. This can help narrow down the issue. Consider adjusting some drivers settings. E.g. $ cat /etc/modprobe.d/nvidia.conf options nvidia NVreg_DynamicPowerManagement=0 options nvidia NVreg_EnableGpuFirmwareLogs=2 options nvidia NVreg_EnablePCIeGen3=1 options nvidia NVreg_EnableResizableBar=1 options nvidia NVreg_EnableStreamMemOPs=1 options nvidia NVreg_InitializeSystemMemoryAllocations=1 options nvidia NVreg_PreserveVideoMemoryAllocations=1 options nvidia NVreg_ResmanDebugLevel=2 options nouveau modeset=0 blacklist nouveau Especially NVreg_EnableGpuFirmwareLogs or NVreg_ResmanDebugLevel can generate more logs to help to debug the issue. Once edited, run sudo update-initramfs -u to apply on the next reboot. For check for other supported parameters, run: modinfo nvidia. After reboot, keep monitoring logs by sudo dmesg, tail -f /var/log/kern.log or sudo journalctl -kf. Consider upgrading BIOS firmware. Kernel timeout issues (e.g. Error while waiting for GPU progress). Suggestions: Increase timeout by echo 600 | sudo tee /proc/sys/kernel/hung_task_timeout_secs. For permanent change, set kernel.hung_task_timeout_secs=600 in newly created /etc/sysctl.d/44-hung_task_timeout_secs.conf file. Or use 0 to disable. Hardware issues. Suggestions: Ensure your card(s) are properly screwed and cables are connected correctly. Ensure you don't move with any cables by accident while card is in use (GPU/monitor cables). Try switching GPU to different slots. For multiple GPUs, try disable one by one. On some motherboards, you can find small switches to do that without need to take the cards physically. Contact your company which assembled your PC, alternatively NVIDIA support (forum or technical support). -
Test also :
nvidia-smi -pm 1 nvidia-smi -lgc 1000,1000 nvidia-smi -pl 150 -
-
Install : https://github.com/apnex/nvidia-driver-injector
sudo git clone https://github.com/apnex/nvidia-driver-injector /root/nvidia-driver-injector cd /root/nvidia-driver-injector sudo ./scripts/apply.sh -
Résultat :
# sudo ./scripts/apply.sh === 0/10 conflict check (apnex/aorus-5090-egpu artifacts?) === no aorus-egpu artifacts detected === 1/10 kernel cmdline (grubby) === grubby not present (non-Fedora-family host?). Set the following kernel cmdline args yourself, by whatever means your distro uses: iommu=off intel_iommu=off thunderbolt.host_reset=false pcie_aspm.policy=performance thunderbolt.clx=0 pcie_port_pm=off AORUS GPU not currently enumerated; can't auto-set pci=resource_alignment. Plug in the eGPU and re-run, or set the arg manually using the bridge BDF above your GPU. === 2/10 kernel-devel for 6.17.0-122035-tuxedo === kernel-devel present at /lib/modules/6.17.0-122035-tuxedo/build === 3/10 gpu UNIX group + GID-rewrite in modprobe.d === gpu group exists (gid=987) === 4/10 /etc/modprobe.d/nvidia-driver-injector.conf === installed /etc/modprobe.d/nvidia-driver-injector.conf (NVreg_DeviceFileGID=987) === 5/10 nvidia-driver-injector-bridge-link-cap (binary + systemd unit) === bridge-link-cap installed + enabled === 6/10 udev rules === udev rules installed (perms + audio-disable) === 7/10 Vulkan/EGL/OpenCL ICD disable === /usr/share/vulkan/icd.d/nvidia_icd.x86_64.json not present (driver may not have shipped this ICD) /usr/share/vulkan/implicit_layer.d/nvidia_layers.json already disabled /usr/share/glvnd/egl_vendor.d/10_nvidia.json already disabled /etc/OpenCL/vendors/nvidia.icd already disabled === 8/10 apply bridge-link-cap now (without rebooting) === GPU not currently enumerated; cap will apply at next boot === 9/10 k3s integration (containerd runtime + RuntimeClass) === k3s not present on this host; skipping k3s integration (re-run with k3s installed, or pass --skip-k3s to silence this) === 10/10 summary === Layer 1 install complete. Next steps: 1. Bring up the injector — pick a path: # Path A (dev / single-host): docker-compose cd /root/nvidia-driver-injector && docker compose up -d # Path B (recommended for production): k3s DaemonSet cd /root/nvidia-driver-injector && kubectl apply -f k8s/daemonset.yaml kubectl rollout status -n kube-system ds/nvidia-driver-injector 2. Once ready, bring up your GPU consumer (e.g., vLLM): - Path A: cd /path/to/workload && docker compose up -d - Path B: see docs/consumer-contract.md (nodeSelector + runtimeClassName: nvidia) -
Fichier : /etc/default/grub
GRUB_DEFAULT=0 GRUB_TIMEOUT_STYLE=hidden GRUB_TIMEOUT=0 GRUB_DISTRIBUTOR='tuxedo' GRUB_CMDLINE_LINUX_DEFAULT='quiet splash' GRUB_CMDLINE_LINUX=""Après
GRUB_DEFAULT=0 GRUB_TIMEOUT_STYLE=hidden GRUB_TIMEOUT=0 GRUB_DISTRIBUTOR='tuxedo' GRUB_CMDLINE_LINUX_DEFAULT='quiet splash' GRUB_CMDLINE_LINUX="iommu=off intel_iommu=off thunderbolt.host_reset=false pcie_aspm.policy=performance thunderbolt.clx=0 pcie_port_pm=off pci=resource_alignment"Update :
# sudo update-grub Sourcing file `/etc/default/grub' Sourcing file `/etc/default/grub.d/50-tuxedo-fix-nvidia-preserve-vram-suspend.cfg' Sourcing file `/etc/default/grub.d/90-tuxedo.cfg' Sourcing file `/etc/default/grub.d/tuxedo-theme.cfg' Generating grub configuration file ... Found theme: /usr/share/grub/themes/tuxedo/theme.txt Found linux image: /boot/vmlinuz-6.17.0-122035-tuxedo Found initrd image: /boot/initrd.img-6.17.0-122035-tuxedo Found memtest86+ 64bit EFI image: /boot/memtest86+x64.efi Warning: os-prober will be executed to detect other bootable partitions. Its output will be used to detect bootable binaries on them and create new boot entries. Adding boot menu entry for UEFI Firmware Settings ... done -
Misère …
# llama-bench -m /models/gemma-3-1b-it-q4_k_m.gguf ggml_cuda_init: failed to initialize CUDA: unknown error | model | size | params | backend | ngl | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | pp512 | 393.02 ± 6.23 | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | tg128 | 48.85 ± 1.55 | build: c3d47e696 (10030) # lsmod | grep nvidia_uvm # modprobe nvidia_uvm modprobe: ERROR: ../libkmod/libkmod-module.c:1084 command_do() Error running install command '/bin/false' for module nvidia_uvm: retcode 1 modprobe: ERROR: could not insert 'nvidia_uvm': Invalid argument -
Je vias donc faire une purge :
sudo nvidia-uninstall sudo apt purge -y '^nvidia-*' '^libnvidia-*' sudo rm -r /var/lib/dkms/nvidia sudo apt -y autoremove sudo update-initramfs -c -k `uname -r` sudo update-grub2Et une reinstallation :
# bash ./NVIDIA-Linux-x86_64-610.43.03.run -m=kernel-open -
Nouveau test :
# git clone https://github.com/lokmantsui/aorus-5090-egpu.git -b nvidia-610.43.02-ubuntu-5060ti # cd aorus-5090-egpu # ./install.sh replacing /etc/modprobe.d/nvidia.conf replacing /etc/modprobe.d/nvidia-graphics-drivers.conf replacing /etc/modprobe.d/nvidia-graphics-drivers-kms.conf replacing /etc/modprobe.d/nvidia-power-management.conf installing /etc/modprobe.d/aorus.conf replacing /etc/default/grub installing /usr/local/bin/aorus-bridge installing /usr/local/bin/aorus-modules installing /etc/systemd/system/aorus.service creating directory /etc/systemd/system/nvidia-persistenced.service.d installing /etc/systemd/system/nvidia-persistenced.service.d/aorus.conf installing /etc/udev/rules.d/99-aorus-egpu.rules running update-initramfs -u update-initramfs: Generating /boot/initrd.img-6.17.0-122035-tuxedo running grub-mkconfig -o /boot/grub/grub.cfg Sourcing file `/etc/default/grub' Sourcing file `/etc/default/grub.d/50-tuxedo-fix-nvidia-preserve-vram-suspend.cfg' Sourcing file `/etc/default/grub.d/90-tuxedo.cfg' Sourcing file `/etc/default/grub.d/tuxedo-theme.cfg' Generating grub configuration file ... Found theme: /usr/share/grub/themes/tuxedo/theme.txt Found linux image: /boot/vmlinuz-6.17.0-122035-tuxedo Found initrd image: /boot/initrd.img-6.17.0-122035-tuxedo Found memtest86+ 64bit EFI image: /boot/memtest86+x64.efi Warning: os-prober will be executed to detect other bootable partitions. Its output will be used to detect bootable binaries on them and create new boot entries. Adding boot menu entry for UEFI Firmware Settings ... done reloading systemd manager enabling aorus.service Created symlink /etc/systemd/system/multi-user.target.wants/aorus.service → /etc/systemd/system/aorus.service. reloading udev rules install complete; reboot required -
Le script ne voit pas la bonne carte :
# /usr/local/bin/aorus-bridge detect 0000:00:01.0Je pense qu’il fonctionne seulement quand on a une seule carte.
Je vais donc modifier : /usr/local/bin/aorus-bridge .
J’ai donc :
# lspci -nn | grep -e NVIDIA 01:00.0 VGA compatible controller [0300]: NVIDIA Corporation GA106M [GeForce RTX 3060 Mobile / Max-Q] [10de:2520] (rev a1) 01:00.1 Audio device [0403]: NVIDIA Corporation GA106 High Definition Audio Controller [10de:228e] (rev a1) 05:00.0 VGA compatible controller [0300]: NVIDIA Corporation GB206 [GeForce RTX 5060 Ti] [10de:2d04] (rev a1) 05:00.1 Audio device [0403]: NVIDIA Corporation GB206 High Definition Audio Controller [10de:22eb] (rev a1)En détail :
# udevadm info -q property -p /sys/bus/pci/devices/0000:05:00.0 DEVPATH=/devices/pci0000:00/0000:00:07.0/0000:03:00.0/0000:04:00.0/0000:05:00.0 DRIVER=nvidia PCI_CLASS=30000 PCI_ID=10DE:2D04 PCI_SUBSYS_ID=1458:41CD PCI_SLOT_NAME=0000:05:00.0 MODALIAS=pci:v000010DEd00002D04sv00001458sd000041CDbc03sc00i00 SUBSYSTEM=pci USEC_INITIALIZED=2566746846 ID_PCI_CLASS_FROM_DATABASE=Display controller ID_PCI_SUBCLASS_FROM_DATABASE=VGA compatible controller ID_PCI_INTERFACE_FROM_DATABASE=VGA controller ID_VENDOR_FROM_DATABASE=NVIDIA Corporation ID_PATH=pci-0000:05:00.0 ID_PATH_TAG=pci-0000_05_00_0 ID_FOR_SEAT=pci-pci-0000_05_00_0 TAGS=:seat:master-of-seat:systemd: CURRENT_TAGS=:master-of-seat:seat: # udevadm info -q property -p /sys/bus/pci/devices/0000:01:00.0 DEVPATH=/devices/pci0000:00/0000:00:01.0/0000:01:00.0 DRIVER=nvidia PCI_CLASS=30000 PCI_ID=10DE:2520 PCI_SUBSYS_ID=1D05:1146 PCI_SLOT_NAME=0000:01:00.0 MODALIAS=pci:v000010DEd00002520sv00001D05sd00001146bc03sc00i00 SUBSYSTEM=pci USEC_INITIALIZED=1449305 ID_PCI_CLASS_FROM_DATABASE=Display controller ID_PCI_SUBCLASS_FROM_DATABASE=VGA compatible controller ID_PCI_INTERFACE_FROM_DATABASE=VGA controller ID_VENDOR_FROM_DATABASE=NVIDIA Corporation ID_MODEL_FROM_DATABASE=GA106M [GeForce RTX 3060 Mobile / Max-Q] ID_PATH=pci-0000:01:00.0 ID_PATH_TAG=pci-0000_01_00_0 ID_FOR_SEAT=pci-pci-0000_01_00_0 TAGS=:systemd:master-of-seat:seat: CURRENT_TAGS=:master-of-seat:seat:Je modifier donc modifier :
VENDOR_ID="${VENDOR_ID:-0x10de}" # NVIDIA # DEVICE_ID: exact PCI device id to match (e.g. 0x2b85 for RTX 5090). Leave # empty to match ANY NVIDIA display controller by PCI class — this covers the # whole RTX 50-series (5090=0x2b85, 5060 Ti=0x2d04, …) without a hardcoded list, # in the same spirit as is_tb_tunneled below. Set DEVICE_ID to pin one board. DEVICE_ID="${DEVICE_ID:-0x2d04}" # PCI base class 0x03 = display controller (VGA 0x0300 / 3D 0x0302); selects the # GPU function and excludes its HDMI-audio function (class 0x0403). GPU_CLASS_PREFIX="${GPU_CLASS_PREFIX:-0x03}" -
Mise à jours du fichier : Fichier : /etc/default/grub
GRUB_DEFAULT=0 GRUB_TIMEOUT_STYLE=hidden GRUB_TIMEOUT=0 GRUB_DISTRIBUTOR='tuxedo' GRUB_CMDLINE_LINUX_DEFAULT="quiet splash" GRUB_CMDLINE_LINUX="pci=resource_alignment iommu.passthrough=1 thunderbolt.host_reset=false pcie_aspm.policy=performance thunderbolt.clx=0 pcie_port_pm=off pci=resource_alignment=35@0000:00:01.0"Il a du voir la première carte, je change donc :
GRUB_DEFAULT=0 GRUB_TIMEOUT_STYLE=hidden GRUB_TIMEOUT=0 GRUB_DISTRIBUTOR='tuxedo' GRUB_CMDLINE_LINUX_DEFAULT="quiet splash" GRUB_CMDLINE_LINUX="iommu.passthrough=1 thunderbolt.host_reset=false pcie_aspm.policy=performance thunderbolt.clx=0 pcie_port_pm=off pci=resource_alignment=35@0000:00:05.0" -
Premier bench sans crash :
# nvidia-smi Fri Jul 17 15:23:12 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 595.71.05 Driver Version: 595.71.05 CUDA Version: 13.2 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 3060 ... Off | 00000000:01:00.0 Off | N/A | | N/A 49C P0 28W / 115W | 0MiB / 6144MiB | 2% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ | 1 NVIDIA GeForce RTX 5060 Ti Off | 00000000:05:00.0 Off | N/A | | 30% 36C P0 19W / 180W | 0MiB / 16311MiB | 2% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | No running processes found | +-----------------------------------------------------------------------------------------+ # llama-bench -m /models/gemma-3-1b-it-q4_k_m.gguf ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21656 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15849 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5806 MiB | model | size | params | backend | ngl | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | pp512 | 16697.67 ± 675.30 | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | tg128 | 261.49 ± 2.71 | build: c3d47e696 (10030)Donc important :
- De modifier /etc/default/grub .
- D’utiliser git clone https://github.com/lokmantsui/aorus-5090-egpu.git -b nvidia-610.43.02-ubuntu-5060ti
- De modifier le script /usr/local/bin/aorus-bridge
Bref je dois faire un audit de mon installation.
-
Nouveau test : Qwen3.6-35B-A3B-UD-Q4_K_M.gguf => crash.
# llama-bench -m /models/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21656 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15849 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5806 MiB | model | size | params | backend | ngl | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: | /home/arias/Documents/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:104: CUDA errorModèle Qwen3.6-27B-Q4_K_M.gguf : OK.
# llama-bench -m /models/Qwen3.6-27B-Q4_K_M.gguf ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21656 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15849 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5806 MiB | model | size | params | backend | ngl | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: | | qwen35 27B Q4_K - Medium | 15.65 GiB | 26.90 B | CUDA | -1 | pp512 | 760.71 ± 4.35 | | qwen35 27B Q4_K - Medium | 15.65 GiB | 26.90 B | CUDA | -1 | tg128 | 21.50 ± 0.01 | build: c3d47e696 (10030) -
Test unitaire de carte :
# llama-bench --list-devices ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB Available devices: CUDA0: NVIDIA GeForce RTX 5060 Ti (15888 MiB, 15752 MiB free) CUDA1: NVIDIA GeForce RTX 3060 Laptop GPU (5803 MiB, 5685 MiB free) # llama-bench -m /models/gemma-3-1b-it-q4_k_m.gguf -dev CUDA0 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------------ | --------------: | -------------------: | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | CUDA0 | pp512 | 19952.89 ± 1896.43 | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | CUDA0 | tg128 | 268.47 ± 0.43 | build: c3d47e696 (10030) # llama-bench -m /models/gemma-3-1b-it-q4_k_m.gguf -dev CUDA1 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------------ | --------------: | -------------------: | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | CUDA1 | pp512 | 11023.49 ± 568.09 | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | CUDA1 | tg128 | 229.36 ± 0.40 | build: c3d47e696 (10030) # llama-bench -m /models/gemma-3-1b-it-q4_k_m.gguf -dev CUDA0,CUDA1 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------------ | --------------: | -------------------: | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | CUDA0 | pp512 | 19994.19 ± 1751.94 | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | CUDA0 | tg128 | 268.49 ± 0.38 | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | CUDA1 | pp512 | 11158.41 ± 527.54 | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | CUDA1 | tg128 | 229.10 ± 0.37 | build: c3d47e696 (10030) # llama-bench -m /models/gemma-3-1b-it-q4_k_m.gguf ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | pp512 | 16582.32 ± 1005.41 | | gemma3 1B Q4_K - Medium | 762.49 MiB | 999.89 M | CUDA | -1 | tg128 | 261.64 ± 1.81 | build: c3d47e696 (10030) -
Test :
# du -sh /models/* 769M /models/gemma-3-1b-it-q4_k_m.gguf 889M /models/mmproj-BF16(1).gguf 862M /models/mmproj-BF16.gguf 885M /models/mmproj-F16.gguf 5,3G /models/Qwen3.5-9B-Q4_K_M.gguf 16G /models/Qwen3.6-27B-Q4_K_M.gguf 21G /models/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf # llama-bench -m /models/Qwen3.5-9B-Q4_K_M.gguf -dev CUDA0 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------------ | --------------: | -------------------: | | qwen35 9B Q4_K - Medium | 5.28 GiB | 8.95 B | CUDA | -1 | CUDA0 | pp512 | 3041.38 ± 47.16 | | qwen35 9B Q4_K - Medium | 5.28 GiB | 8.95 B | CUDA | -1 | CUDA0 | tg128 | 70.57 ± 0.04 | build: c3d47e696 (10030) # llama-bench -m /models/Qwen3.6-27B-Q4_K_M.gguf -dev CUDA0 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------------ | --------------: | -------------------: | llama_bench: error: failed to create context with model '/models/Qwen3.6-27B-Q4_K_M.gguf' -
-
Installation d’outils pour Hermes Agent IA :
# apt-get install ripgrep # apt-get install chromium-browser # npx playwright install-deps chromium -
Nouveau test avec /models/Qwen3.6-27B-Q3_K_M.gguf :
# llama-bench -m /models/Qwen3.6-27B-Q3_K_M.gguf -dev CUDA1 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------------ | --------------: | -------------------: | llama_bench: error: failed to load model '/models/Qwen3.6-27B-Q3_K_M.gguf' # llama-bench -m /models/Qwen3.6-27B-Q3_K_M.gguf ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | -1 | pp512 | 707.38 ± 5.11 | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | -1 | tg128 | 18.31 ± 0.01 | build: c3d47e696 (10030) # llama-bench -m /models/Qwen3.6-27B-Q3_K_M.gguf -dev CUDA0 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------------ | --------------: | -------------------: | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | -1 | CUDA0 | pp512 | 841.06 ± 9.58 | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | -1 | CUDA0 | tg128 | 20.50 ± 0.02 | build: c3d47e696 (10030)Pendant le test sur les deux cartes j’ai lancé gpustat , j’ai les deux cartes qui tournent :
# gpustat tuxedo-17 Fri Jul 17 17:14:51 2026 610.43.03 [0] NVIDIA GeForce RTX 3060 Laptop GPU | 58°C, 40 % | 4156 / 6144 MB | root(4148M) [1] NVIDIA GeForce RTX 5060 Ti | 62°C, 60 % | 8916 / 16311 MB | root(8908M)Quand je suis sur CUDA0 :
gpustat tuxedo-17 Fri Jul 17 17:15:48 2026 610.43.03 [0] NVIDIA GeForce RTX 3060 Laptop GPU | 49°C, 0 % | 2 / 6144 MB | [1] NVIDIA GeForce RTX 5060 Ti | 68°C, 100 % | 12882 / 16311 MB | root(12874M) -
Nouveau test :
# llama-bench -m /models/Qwen3.6-27B-Q3_K_M.gguf -dev CUDA0 -fa on --threads 12 -ngl 999 --cache-type-v q8_0 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | threads | type_v | fa | dev | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | -----: | --: | ------------ | --------------: | -------------------: | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | 999 | 12 | q8_0 | 1 | CUDA0 | pp512 | 387.17 ± 2.25 | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | 999 | 12 | q8_0 | 1 | CUDA0 | tg128 | 18.31 ± 0.01 | # llama-bench -m /models/Qwen3.6-27B-Q3_K_M.gguf -fa on --threads 12 -ngl 999 --cache-type-v q8_0 ggml_cuda_init: found 2 CUDA devices (Total VRAM: 21692 MiB): Device 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0, VMM: yes, VRAM: 15888 MiB Device 1: NVIDIA GeForce RTX 3060 Laptop GPU, compute capability 8.6, VMM: yes, VRAM: 5803 MiB | model | size | params | backend | ngl | threads | type_v | fa | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | -----: | --: | --------------: | -------------------: | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | 999 | 12 | q8_0 | 1 | pp512 | 367.28 ± 1.88 | | qwen35 27B Q3_K - Medium | 12.64 GiB | 26.90 B | CUDA | 999 | 12 | q8_0 | 1 | tg128 | 16.71 ± 0.03 |
Bonjour ! Vous semblez intéressé par cette conversation, mais vous n’avez pas encore de compte.
Marre de refaire défiler les mêmes messages ? Créez un compte pour retrouver votre position, recevoir des notifications des nouvelles réponses, sauvegarder vos favoris et voter pour les messages que vous appréciez.
Grâce à votre participation, ce message peut devenir encore meilleur 💗
S'inscrire Se connecter