👾How to install LM Studio CLI in Linux Terminal

LM Studio CLI installation guide without a UI in a terminal instance.

1. Open a new terminal to run LM Studio CLI, or use tmux

2. Get LM Studio or run below (1GB or so download size)

wget https://lmstudio.ai/download/latest/linux/x64?format=AppImage -O 'LM_Studio.AppImage'
chmod u+x ./LM_Studio.AppImage

1. Run LM Studio via

./LM_Studio.AppImage

You might see below:

[802435:0215/073628.027773:FATAL:sandbox/linux/suid/client/setuid_sandbox_host.cc:166] The SUID sandbox helper binary was found, but is not configured correctly. Rather than run without sandboxing I'm aborting now.

If so, do the below instead:

./LM_Studio.AppImage --no-sandbox

1. You then might see the below, especially if you are in a cloud instance with no desktop:

[807101:0215/073740.801969:ERROR:ui/ozone/platform/x11/ozone_platform_x11.cc:249] Missing X server or $DISPLAY
[807101:0215/073740.802000:ERROR:ui/aura/env.cc:257] The platform failed to initialize.  Exiting.
Segmentation fault (core dumped)

If so, install a "fake" desktop simulator within the terminal:

sudo apt-get install xvfb

1. Then use xvfb and launch LM Studio:

xvfb-run --auto-servernum ./LM_Studio.AppImage --no-sandbox

1. Then get LM Studio's LMS / CLI in another terminal, or after CTRL+B+D for tmux

~/.lmstudio/bin/lms bootstrap

1. Open a new terminal or tmux then run:

lms

If you see -bash: lms: command not found please run lms in a new terminal window!

1. Now download a model like Qwen3-Coder-Next like below. If downloads get stuck, see Hugging Face Hub, XET debugging

pip install -U huggingface_hub
hf download unsloth/Qwen3-Coder-Next-GGUF \
    --local-dir unsloth/Qwen3-Coder-Next-GGUF \
    --include "*UD-Q4_K_XL*"

1. We then import the model via:

lms import \
    unsloth/Qwen3-Coder-Next-GGUF/Qwen3-Coder-Next-UD-Q4_K_XL.gguf \
    --symbolic-link --user-repo "unsloth/Qwen3-Coder-Next-GGUF" -y

You might see EEXIST: file already exists, symlink 'unsloth/Qwen3-Coder-Next-GGUF/UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00001-of-00003.gguf' -> '~/.lmstudio/models/unsloth/Qwen3-Coder-Next-GGUF/Qwen3-Coder-Next-UD-Q6_K_XL-00001-of-00003.gguf' which just means you already have the model loaded in LM Studio.

You can also check all LM Studio models via:

ls ~/.lmstudio/models

1. You can also get models via lms get via below:

lms get https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF@Q4_K_XL

You will then see:

Finalizing download...
Download completed. You can load the model with: 
lms load qwen3-coder-next

Then load lms load qwen3-coder-next:

1. Then start up LM Studio's server:

lms server start --port 8001 --bind 127.0.0.1

You will see Success! Server is now running on port 8001

1. Then in a new terminal, use the model via the OpenAI compatible endpoint:

from openai import OpenAI
import json
openai_client = OpenAI(
    base_url = "http://127.0.0.1:8001/v1",
    api_key = "null",
)
model_name = next(iter(openai_client.models.list())).id
print(model_name)
completion = openai_client.chat.completions.create(
    model = model_name,
    messages = [{"role": "user", "content": "What is 2+2?"},],
)
print(completion.choices[0].message.content)

And we're done!