github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #14119] Ollama suddenly stopped using Nvidia on hybrid GPU laptop #9212

New Issue
Closed
opened 2026-04-12 22:04:26 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 22:04:26 -05:00
Owner
Copy Link

Originally created by @JoaoHCopetti on GitHub (Feb 6, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14119

What is the issue?

I've a laptop with Nvidia/AMD and it's using only CPU, I tried lfm2.5-thinking which is a pretty small model (1.2B) and huihui/qwen3-abliterated:8b (8B).

This is my output on nvidia-smi

Image 
OS: Arch Linux x86_64
Host: 82MJ (IdeaPad Gaming 3 15ACH6)
Kernel: Linux 6.18.7-arch1-1
Packages: 836 (pacman)
DE: GNOME 49.3
WM: Mutter (Wayland)
CPU: AMD Ryzen 7 5800H (16) @ 4.46 GHz
GPU 1: NVIDIA GeForce GTX 1650 Mobile / Max-Q [Discrete]
GPU 2: AMD Radeon Vega Series / Radeon Vega Mobile Series [Integrated]
Memory: 2.67 GiB / 13.50 GiB (20%)
Swap: 4.00 KiB / 6.75 GiB (0%)

❯ ollama ps                 
NAME                      ID              SIZE      PROCESSOR    CONTEXT    UNTIL              
lfm2.5-thinking:latest    95bd9d45385f    956 MB    100% CPU     4096       4 minutes from now

Secure boot disabled.
I'm using arch with archinstall script.
Ollama version is 0.15.4

Relevant log output

fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.970-03:00 level=INFO source=server.go:245 msg="enabling flash attention"
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.971-03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-a7b19185f31650af480c3fa28dd240c75862182e0f30b118dbfadb192e4beb0a --port 37909"
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.971-03:00 level=INFO source=sched.go:452 msg="system memory" total="13.5 GiB" free="10.8 GiB" free_swap="6.7 GiB"
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.971-03:00 level=INFO source=server.go:755 msg="loading model" "model layers"=17 requested=-1
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.980-03:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.980-03:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:37909"
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.983-03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:136 msg="" architecture=lfm2 file_type=Q4_K_M name="" description="" num_tensors=148 num_key_values=28
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.002-03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=ggml.go:482 msg="offloading 0 repeating layers to GPU"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=ggml.go:494 msg="offloaded 0/17 layers to GPU"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="799.8 MiB"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="48.1 MiB"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="64.0 MiB"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=device.go:272 msg="total memory" size="911.9 MiB"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=sched.go:526 msg="loaded runners" count=1
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=server.go:1347 msg="waiting for llama runner to start responding"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.033-03:00 level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model"
fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.284-03:00 level=INFO source=server.go:1385 msg="llama runner started in 0.31 seconds"

OS

Arch Linux

GPU

NVIDIA GeForce GTX 1650

CPU

AMD Ryzen 7 5800H (16) @ 4.46 GHz

Ollama version

0.15.4

Originally created by @JoaoHCopetti on GitHub (Feb 6, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14119 ### What is the issue? I've a laptop with Nvidia/AMD and it's using only CPU, I tried `lfm2.5-thinking` which is a pretty small model (1.2B) and `huihui/qwen3-abliterated:8b` (8B). This is my output on `nvidia-smi` <img width="1012" height="616" alt="Image" src="https://github.com/user-attachments/assets/5f1d0dc2-e2e3-41f9-abfa-779221358b75" /> ``` OS: Arch Linux x86_64 Host: 82MJ (IdeaPad Gaming 3 15ACH6) Kernel: Linux 6.18.7-arch1-1 Packages: 836 (pacman) DE: GNOME 49.3 WM: Mutter (Wayland) CPU: AMD Ryzen 7 5800H (16) @ 4.46 GHz GPU 1: NVIDIA GeForce GTX 1650 Mobile / Max-Q [Discrete] GPU 2: AMD Radeon Vega Series / Radeon Vega Mobile Series [Integrated] Memory: 2.67 GiB / 13.50 GiB (20%) Swap: 4.00 KiB / 6.75 GiB (0%) ``` ``` ❯ ollama ps NAME ID SIZE PROCESSOR CONTEXT UNTIL lfm2.5-thinking:latest 95bd9d45385f 956 MB 100% CPU 4096 4 minutes from now ``` Secure boot disabled. I'm using `arch` with `archinstall` script. Ollama version is 0.15.4 ### Relevant log output ```shell fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.970-03:00 level=INFO source=server.go:245 msg="enabling flash attention" fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.971-03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-a7b19185f31650af480c3fa28dd240c75862182e0f30b118dbfadb192e4beb0a --port 37909" fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.971-03:00 level=INFO source=sched.go:452 msg="system memory" total="13.5 GiB" free="10.8 GiB" free_swap="6.7 GiB" fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.971-03:00 level=INFO source=server.go:755 msg="loading model" "model layers"=17 requested=-1 fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.980-03:00 level=INFO source=runner.go:1405 msg="starting ollama engine" fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.980-03:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:37909" fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.983-03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:136 msg="" architecture=lfm2 file_type=Q4_K_M name="" description="" num_tensors=148 num_key_values=28 fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.002-03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:8 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=ggml.go:482 msg="offloading 0 repeating layers to GPU" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=ggml.go:494 msg="offloaded 0/17 layers to GPU" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.030-03:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="799.8 MiB" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="48.1 MiB" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="64.0 MiB" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=device.go:272 msg="total memory" size="911.9 MiB" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=sched.go:526 msg="loaded runners" count=1 fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.031-03:00 level=INFO source=server.go:1347 msg="waiting for llama runner to start responding" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.033-03:00 level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model" fev 06 09:41:02 arch ollama[1703]: time=2026-02-06T09:41:02.284-03:00 level=INFO source=server.go:1385 msg="llama runner started in 0.31 seconds" ``` ### OS Arch Linux ### GPU NVIDIA GeForce GTX 1650 ### CPU AMD Ryzen 7 5800H (16) @ 4.46 GHz ### Ollama version 0.15.4
GiteaMirror added the bug label 2026-04-12 22:04:26 -05:00
GiteaMirror commented 2026-04-12 22:04:27 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 6, 2026):

fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:136 msg="" architecture=lfm2 file_type=Q4_K_M name="" description="" num_tensors=148 num_key_values=28
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)

No backend accelerators found. Set OLLAMA_DEBUG=2 in the server environment, restart the ollama server, and post the output of the following:

journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" | sed -ne '/server config/,/inference compute/p'
<!-- gh-comment-id:3860519245 --> @rick-github commented on GitHub (Feb 6, 2026): ``` fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:136 msg="" architecture=lfm2 file_type=Q4_K_M name="" description="" num_tensors=148 num_key_values=28 fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) ``` No backend accelerators found. Set `OLLAMA_DEBUG=2` in the server environment, restart the ollama server, and post the output of the following: ``` journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" | sed -ne '/server config/,/inference compute/p' ```
GiteaMirror commented 2026-04-12 22:04:28 -05:00
Author
Owner
Copy Link

@JoaoHCopetti commented on GitHub (Feb 7, 2026):

fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:136 msg="" architecture=lfm2 file_type=Q4_K_M name="" description="" num_tensors=148 num_key_values=28
fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)

No backend accelerators found. Set OLLAMA_DEBUG=2 in the server environment, restart the ollama server, and post the output of the following:

journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" | sed -ne '/server config/,/inference compute/p'

I edit it via sudo systemctl edit ollama command.
Then sudo systemctl daemon-reload and sudo systemctl restart ollama.
Then I ran ollama run lfm2.5-thinking and entered "hi":

Here's the output from the command you suggested (not running as sudo):

fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.181-03:00 level=INFO source=routes.go:1631 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.182-03:00 level=INFO source=images.go:473 msg="total blobs: 16"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=INFO source=routes.go:1684 msg="Listening on 127.0.0.1:11434 (version 0.15.4)"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=DEBUG source=sched.go:121 msg="starting llm scheduler"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs=[/usr/local/lib/ollama] extraEnvs=map[]
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.184-03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46569"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.184-03:00 level=DEBUG source=server.go:430 msg=subprocess PATH=/home/joao/.local/bin:/home/joao/.local/share/pnpm:/run/user/1000/fnm_multishells/6168_1769694314971/bin:/home/joao/.local/share/fnm:/home/joao/.local/share/zinit/polaris/bin:/usr/local/bin:/usr/bin:/usr/local/sbin:/usr/bin/site_perl:/usr/bin/vendor_perl:/usr/bin/core_perl OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/local/lib/ollama OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.193-03:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.194-03:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:46569"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.file_type default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.name default=""
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.description default=""
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.196-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.block_count default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.pooling_type default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.expert_count default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.pre default=""
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.block_count default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.embedding_length default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.attention.head_count default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.attention.head_count_kv default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.attention.key_length default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.rope.dimension_count default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.rope.freq_base default=100000
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.rope.scaling.factor default=1
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=2.058559ms
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=1.467µs
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH=[/usr/local/lib/ollama] devices=[]
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=14.012649ms OLLAMA_LIBRARY_PATH=[/usr/local/lib/ollama] extra_envs=map[]
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[]
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=14.343216ms
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="13.5 GiB" available="10.5 GiB"
<!-- gh-comment-id:3863371899 --> @JoaoHCopetti commented on GitHub (Feb 7, 2026): > ``` > fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:136 msg="" architecture=lfm2 file_type=Q4_K_M name="" description="" num_tensors=148 num_key_values=28 > fev 06 09:41:01 arch ollama[1703]: time=2026-02-06T09:41:01.993-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) > ``` > > No backend accelerators found. Set `OLLAMA_DEBUG=2` in the server environment, restart the ollama server, and post the output of the following: > > ``` > journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" | sed -ne '/server config/,/inference compute/p' > ``` I edit it via `sudo systemctl edit ollama` command. Then `sudo systemctl daemon-reload` and `sudo systemctl restart ollama`. Then I ran `ollama run lfm2.5-thinking` and entered "hi": Here's the output from the command you suggested (not running as sudo): ``` fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.181-03:00 level=INFO source=routes.go:1631 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.182-03:00 level=INFO source=images.go:473 msg="total blobs: 16" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=INFO source=routes.go:1684 msg="Listening on 127.0.0.1:11434 (version 0.15.4)" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=DEBUG source=sched.go:121 msg="starting llm scheduler" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.183-03:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs=[/usr/local/lib/ollama] extraEnvs=map[] fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.184-03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46569" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.184-03:00 level=DEBUG source=server.go:430 msg=subprocess PATH=/home/joao/.local/bin:/home/joao/.local/share/pnpm:/run/user/1000/fnm_multishells/6168_1769694314971/bin:/home/joao/.local/share/fnm:/home/joao/.local/share/zinit/polaris/bin:/usr/local/bin:/usr/bin:/usr/local/sbin:/usr/bin/site_perl:/usr/bin/vendor_perl:/usr/bin/core_perl OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/local/lib/ollama OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.193-03:00 level=INFO source=runner.go:1405 msg="starting ollama engine" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.194-03:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:46569" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.file_type default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.name default="" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.description default="" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.196-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.block_count default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.pooling_type default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.expert_count default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=tokenizer.ggml.pre default="" fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.block_count default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.embedding_length default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.attention.head_count default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.attention.head_count_kv default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.attention.key_length default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.rope.dimension_count default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.rope.freq_base default=100000 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=ggml.go:298 msg="key with type not found" key=llama.rope.scaling.factor default=1 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=2.058559ms fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=1.467µs fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH=[/usr/local/lib/ollama] devices=[] fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=14.012649ms OLLAMA_LIBRARY_PATH=[/usr/local/lib/ollama] extra_envs=map[] fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0 fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[] fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=14.343216ms fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.197-03:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="13.5 GiB" available="10.5 GiB" ```
GiteaMirror commented 2026-04-12 22:04:29 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 7, 2026):

fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.196-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)

No accelerator backends detected. How did you install ollama?

What's the output of

/usr/local/lib/ollama
<!-- gh-comment-id:3863384467 --> @rick-github commented on GitHub (Feb 7, 2026): ``` fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.196-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) ``` No accelerator backends detected. How did you install ollama? What's the output of ``` /usr/local/lib/ollama ```
GiteaMirror commented 2026-04-12 22:04:30 -05:00
Author
Owner
Copy Link

@JoaoHCopetti commented on GitHub (Feb 7, 2026):

fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.196-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)

No accelerator backends detected. How did you install ollama?

What's the output of

/usr/local/lib/ollama

I installed using the Linux script on download page: https://ollama.com/download

ls /usr/local/lib/ollama              
cuda_v12

sudo ls /usr/local/lib/ollama/cuda_v12
libcublasLt.so.12  libcublasLt.so.12.8.4.1  libcublas.so.12  libcublas.so.12.8.4.1  libcudart.so.12.8.90  libggml-cuda.so
<!-- gh-comment-id:3863388933 --> @JoaoHCopetti commented on GitHub (Feb 7, 2026): > ``` > fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.195-03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama > fev 06 23:25:30 arch ollama[21895]: time=2026-02-06T23:25:30.196-03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) > ``` > > No accelerator backends detected. How did you install ollama? > > What's the output of > > ``` > /usr/local/lib/ollama > ``` I installed using the Linux script on download page: https://ollama.com/download ``` ls /usr/local/lib/ollama cuda_v12 ``` ``` sudo ls /usr/local/lib/ollama/cuda_v12 libcublasLt.so.12 libcublasLt.so.12.8.4.1 libcublas.so.12 libcublas.so.12.8.4.1 libcudart.so.12.8.90 libggml-cuda.so ```
GiteaMirror commented 2026-04-12 22:04:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 7, 2026):

Your installation is incomplete, it should look like:

/usr/local/lib/ollama:
total 6484
drwxr-xr-x 2 root root    4096 Feb  6 02:30 cuda_v12
drwxr-xr-x 2 root root    4096 Feb  6 02:21 cuda_v13
lrwxrwxrwx 1 root root      17 Feb  6 02:08 libggml-base.so -> libggml-base.so.0
lrwxrwxrwx 1 root root      21 Feb  6 02:08 libggml-base.so.0 -> libggml-base.so.0.0.0
-rwxr-xr-x 1 root root  748152 Feb  6 02:08 libggml-base.so.0.0.0
-rwxr-xr-x 1 root root  873912 Feb  6 02:08 libggml-cpu-alderlake.so
-rwxr-xr-x 1 root root  873912 Feb  6 02:08 libggml-cpu-haswell.so
-rwxr-xr-x 1 root root 1009080 Feb  6 02:08 libggml-cpu-icelake.so
-rwxr-xr-x 1 root root  820728 Feb  6 02:08 libggml-cpu-sandybridge.so
-rwxr-xr-x 1 root root 1009080 Feb  6 02:08 libggml-cpu-skylakex.so
-rwxr-xr-x 1 root root  636536 Feb  6 02:08 libggml-cpu-sse42.so
-rwxr-xr-x 1 root root  632472 Feb  6 02:08 libggml-cpu-x64.so
drwxr-xr-x 2 root root    4096 Feb  6 02:31 mlx_cuda_v13
drwxr-xr-x 2 root root    4096 Feb  6 02:08 vulkan

/usr/local/lib/ollama/cuda_v12:
total 2497492
lrwxrwxrwx 1 root root         23 Feb  6 02:30 libcublasLt.so.12 -> libcublasLt.so.12.8.4.1
-rwxr-xr-x 1 root root  751771728 Jul  8  2015 libcublasLt.so.12.8.4.1
lrwxrwxrwx 1 root root         21 Feb  6 02:30 libcublas.so.12 -> libcublas.so.12.8.4.1
-rwxr-xr-x 1 root root  116388640 Jul  8  2015 libcublas.so.12.8.4.1
lrwxrwxrwx 1 root root         20 Feb  6 02:30 libcudart.so.12 -> libcudart.so.12.8.90
-rwxr-xr-x 1 root root     728800 Jul  8  2015 libcudart.so.12.8.90
-rwxr-xr-x 1 root root 1688520016 Feb  6 02:30 libggml-cuda.so

I recommend re-installing.

<!-- gh-comment-id:3863400932 --> @rick-github commented on GitHub (Feb 7, 2026): Your installation is incomplete, it should look like: ``` /usr/local/lib/ollama: total 6484 drwxr-xr-x 2 root root 4096 Feb 6 02:30 cuda_v12 drwxr-xr-x 2 root root 4096 Feb 6 02:21 cuda_v13 lrwxrwxrwx 1 root root 17 Feb 6 02:08 libggml-base.so -> libggml-base.so.0 lrwxrwxrwx 1 root root 21 Feb 6 02:08 libggml-base.so.0 -> libggml-base.so.0.0.0 -rwxr-xr-x 1 root root 748152 Feb 6 02:08 libggml-base.so.0.0.0 -rwxr-xr-x 1 root root 873912 Feb 6 02:08 libggml-cpu-alderlake.so -rwxr-xr-x 1 root root 873912 Feb 6 02:08 libggml-cpu-haswell.so -rwxr-xr-x 1 root root 1009080 Feb 6 02:08 libggml-cpu-icelake.so -rwxr-xr-x 1 root root 820728 Feb 6 02:08 libggml-cpu-sandybridge.so -rwxr-xr-x 1 root root 1009080 Feb 6 02:08 libggml-cpu-skylakex.so -rwxr-xr-x 1 root root 636536 Feb 6 02:08 libggml-cpu-sse42.so -rwxr-xr-x 1 root root 632472 Feb 6 02:08 libggml-cpu-x64.so drwxr-xr-x 2 root root 4096 Feb 6 02:31 mlx_cuda_v13 drwxr-xr-x 2 root root 4096 Feb 6 02:08 vulkan /usr/local/lib/ollama/cuda_v12: total 2497492 lrwxrwxrwx 1 root root 23 Feb 6 02:30 libcublasLt.so.12 -> libcublasLt.so.12.8.4.1 -rwxr-xr-x 1 root root 751771728 Jul 8 2015 libcublasLt.so.12.8.4.1 lrwxrwxrwx 1 root root 21 Feb 6 02:30 libcublas.so.12 -> libcublas.so.12.8.4.1 -rwxr-xr-x 1 root root 116388640 Jul 8 2015 libcublas.so.12.8.4.1 lrwxrwxrwx 1 root root 20 Feb 6 02:30 libcudart.so.12 -> libcudart.so.12.8.90 -rwxr-xr-x 1 root root 728800 Jul 8 2015 libcudart.so.12.8.90 -rwxr-xr-x 1 root root 1688520016 Feb 6 02:30 libggml-cuda.so ``` I recommend re-installing.
GiteaMirror commented 2026-04-12 22:04:30 -05:00
Author
Owner
Copy Link

@JoaoHCopetti commented on GitHub (Feb 7, 2026):

Reinstalling worked, thank you.

Not sure how this happened tho, it was working fine. I don't use antivirus or anything, not sure how those files got deleted.

<!-- gh-comment-id:3863420118 --> @JoaoHCopetti commented on GitHub (Feb 7, 2026): Reinstalling worked, thank you. Not sure how this happened tho, it was working fine. I don't use antivirus or anything, not sure how those files got deleted.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9212
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?