#12081·LocalAI

localai cannot run the recommended model

Author: guystreeterCreated Sep 16, 2026Updated Sep 16, 2026
Labelsbugunconfirmed

LocalAI version:

quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda-13 pulled today

Environment, CPU architecture, OS, and Version:

Linux beast.local 7.2.5-200.fc44.x86_64 #1 SMP PREEMPT_DYNAMIC Fri Sep 11 15:11:05 UTC 2026 x86_64 GNU/Linux
Tue Sep 15 21:41:49 2026       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 615.71.09              KMD Version: 615.71.09     CUDA UMD Version: 13.4     |
+-----------------------------------------+------------------------+----------------------+
| 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 4070 Ti     Off |   00000000:05:00.0 Off |                  N/A |
|  0%   31C    P8              6W /  285W |     164MiB /  12282MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A            1846      G   /usr/bin/gnome-shell                    121MiB |
|    0   N/A  N/A            3407      G   /usr/bin/Xwayland                         3MiB |
+-----------------------------------------------------------------------------------------+

Describe the bug

On a fresh install, localai recommends spark-x2.5-4b. I download and run it, and I get

Error: failed to load model with internal loader: could not load model: rpc error: code = Internal desc = Failed to load model: /models/llama-cpp/models/Spark-X2.5-4B-Q4_K_M/Spark-X2.5-4B-Q4_K_M.gguf. Error: llama_model_load: error loading model: unknown model architecture: 'spark2_5'; llama_model_load_from_file_impl: failed to load model; llama_model_load: error loading model: unknown model architecture: 'spark2_5'; llama_model_load_from_file_impl: failed to load model

To Reproduce

Fresh install, install and start the recommended model. Fails consistently