Fine-tune this chat. Blank fields use your defaults from Settings › Chat (system prompt, sampling); set one here to override it for this conversation only.
Advanced sampling, seed, grammar
Coder session
Destructive actions ask for your approval below, unless you enable
auto-approve. Runs the localcoder agent against a project directory; it can read,
write, and run code.
Models
Find models
Types
Format
Add a model
From HuggingFace (owner/repo[:file.gguf]) or an https URL, or add one already on disk - paste a folder/file path, or use Browse to pick a folder.
Already have models in a ComfyUI install? Preview and import them in bulk.
Picks up new models from the ComfyUI folder already set in Settings - one click, no folder picker.
Registered models
Image generation
Runs your local ComfyUI FLUX pipeline. The LLM unloads automatically
to free VRAM for the image model, and reloads on the next chat request.
Tick thumbnails to select for bulk actions; click one for
details, metadata, and per-image actions.
Workflow
The ComfyUI workflow this page uses. Upload one (in
ComfyUI: Save -> API format) and select it, or keep the built-in default.
Music generation
Runs the ACE-Step workflow on your local ComfyUI (same VRAM
handover as image generation). Track length is arbitrary; longer tracks just
take longer.
Generate
Advanced seed, steps, CFG
History
Tick a card to select it for bulk actions; click one for
details, metadata, and per-track actions.
Workflow
The ComfyUI workflow this page uses. Upload one (in
ComfyUI: Save -> API format) and select it, or keep the built-in default.
Video generation
Slowest generator here: minutes to hours per clip, so iterate
with short durations and fewer steps. Keep the native 1280×704 resolution
or quality collapses. Runs Wan 2.2 on your local ComfyUI.
Generate
Advanced resolution, seed, steps, CFG
History
Tick a card to select it for bulk actions; click one for
details, metadata, and per-clip actions.
Workflow
The ComfyUI workflow this page uses. Upload one (in
ComfyUI: Save -> API format) and select it, or keep the built-in default.
Knowledge
Index folders or files into collections, then pick a collection in
the chat parameters drawer - replies get grounded in the most relevant excerpts,
with citations. Retrieval is BM25 (always works offline); when an embedding model is
set up, semantic (vector) search is blended in. Collections live in the
localm data directory under rag/.
Embedding model
Semantic search uses a small embedding model, loaded separately from
your chat model. Choose the built-in one (downloaded once, on this machine) or any
model from your list. BM25 lexical search always works without one.
Checking…
New collection
Collections
Plugins
LocaLM is a model loader plus a plugin engine. Only chat is active out of
the box; install the others as you need them. Enabling or disabling a plugin takes effect
instantly - no restart, no model reload.
First-party plugins
External plugins
A third-party plugin is a folder with a plugin.toml manifest
under ~/.localm/plugins/; it can add a CLI command and export tools to the
coder agent. Installation is a local directory copy.
Settings
Stored in config.json in your data directory. Pick a section on the left;
each one saves on its own. Engine values apply on the next model load.
Live tuning (apply now)
Adjust the running model without a reload: how much of it is on the GPU,
and how large its context window is. Runtime & GPU holds the persisted next-load
defaults; these apply right now. The VRAM figure is an estimate.
Backend: -
An NVIDIA GPU was detected; the CUDA backend usually performs better than the
currently installed Vulkan backend. localm never switches this for you - pick
cuda under Settings > Updates > Inference runtime if you want
to try it.
How much of the model to offload to the GPU (0-999).
The most tokens the model can attend to
(4096).
estimate unavailable
Which device the model loads onto. Saves immediately;
applies on the next model load.
Spread a model too large for one card over several
(check 2 or more, which overrides Main GPU). Each card's share follows
its free VRAM at load time, unless pinned below. Saves immediately;
applies on the next model load.
Optional relative
weight per checked device (e.g. 3 and 1 gives the first card three
times the second's share). Leave every weight blank to keep the
automatic free-VRAM sizing above.
How many models may stay loaded at once. Blank lets free-VRAM
arithmetic decide (a model loads alongside the others only when it provably
fits); 1 forces strict single-resident. Saves immediately.
Names that are never evicted to make room for another model.
Protects an already-loaded model; it never loads one. Saves immediately.
Appearance
How the wordmark is drawn in the sidebar. Saved in this browser only.
Owner key
The one key that grants full access to this server - the
named keys below are limited slices of it. Roll it if it may have leaked,
or set one you already use. This browser stays signed in; every other
device keeps working only once you give it the new key.
Keys & devices
Mint a named, scope-limited key to pair another device
or person - each key gets only the capabilities you check, and a QR is
shown to scan (no typing). A coder key is restricted (read +
edit, no shell); coder (full) and admin are owner-only.
The secret is shown once - revoke a key to unpair that device.
Sign in on this device
Save an API key on this device (a secure cookie) so you stay signed in.
Leave blank and Save to sign out.
Companion app
This app talks only to the server that served it. To use LocaLM on your
phone, open one of these addresses on the phone (on the same Wi-Fi, or over a private
network like Tailscale), trust the certificate once, and install it from there.
Pair a phone: open LocaLM on the phone, tap Scan QR code on the
onboarding screen, and point it at this code to copy the API key over - no typing.
Use your browser's Install app /
Add to Home screen to pin LocaLM as an app.
Add to Home Screen (iPhone / iPad):
Open this page in Safari.
Tap the Share button (the square with an up-arrow).
Choose Add to Home Screen, then Add.
Server controls
Control this LocaLM server from here instead of force-closing
the window (which can crash without a clean unload). The model is unloaded first
either way. Restart brings the server back automatically; Shut down stops it (start
it again from your launcher or terminal).
Other running instances
Each localm gui/localm serve you start
advertises itself, so other launches can find it instead of double-loading a model.
This lists every one running on this machine right now (the server behind this page
is not shown here - use Server controls above for that).
Your data
Erase the conversations stored on this device. This cannot be undone.
Report a bug
Describe what went wrong. We save an editable report to your
data folder with a safe diagnostic snapshot (OS, GPU, backend, loaded model,
settings subset, dependency versions, recent activity, and any browser console
errors) - never your API key, config secrets, or chat content. You can review
and send it to the maintainer.
Changelog
See what changed in each localm release - the full version
history, newest first.
Updates
App update
Check for a newer localm build. You always start it - localm
never updates itself. Most updates apply with just a restart.
Roll back
Restore the build you were running before the last update,
then restart. This is for an update that applied cleanly but turned out worse.
It restores that build's files; it does not undo package installs an update
made along the way.
App launcher
Rebuild the native launcher (LocaLM.exe on Windows, the
LocaLM menu entry on Linux) so Task Manager and the taskbar show LocaLM
instead of python. Needed again after a Python upgrade, which replaces
the interpreter this launcher is a copy of.
Inference runtime
Check for a newer llama.cpp runtime build for your installed
backend, or install one on a machine that has none yet. You always start it -
it never re-provisions on its own. A build that fails to load on this machine
is never kept: setup-llama walks back to an older one that does.
Which prebuilt to install. Changing this re-downloads the
runtime; nothing is replaced while a model is loaded, and your pick is never
swapped silently if it turns out not to load here.
Optional. A llama.cpp release tag such as
b10355 installs exactly that build and pins it;
default returns to the build localm ships and confirmed, and
latest tracks upstream's newest, which localm has not tested.
Update behavior
Diagnostics
Run localm's active self-checks - the same ones
localm doctor performs in a terminal. They try the things that
silently break an install: loading the runtime, spawning the worker process
every model load needs, and creating a nested venv. Nothing is installed or
changed, and a run takes about half a minute.
Issues
Open and resolved issues for this project (read-only) - see
whether a bug you reported has been fixed.
Logs
Copy every log file of this running instance into a folder you
choose - handy when sending diagnostics. Each export goes into its own
timestamped subfolder, so nothing is overwritten.
Upload files
Send files from this device or your phone into localm's
uploads folder, so models and tools can read them. They are stored
on the host, separate from chat attachments. Large model weights use the model
downloader instead.
Artifact
Connect to LocaLM
This LocaLM server requires an API key.
Trust this device's certificate
LocaLM secures the connection with its own certificate.
Install it once to remove the browser's "not secure" warning and to enable
Install app.
You're using Firefox. Firefox keeps its own certificate store, so a
Windows install won't remove the warning here. Open the downloaded file and
import it under Authorities (check "Trust this CA to identify
websites"), or set security.enterprise_roots.enabled to
true in about:config to reuse the Windows store.
How do I install it?
Firefox (any OS): Firefox uses its OWN certificate store, so a
Windows / system install does not cover it. Open the downloaded file, or
go to Settings → Privacy & Security → Certificates →
View Certificates → Authorities → Import, and check "Trust this
CA to identify websites". (Or set
security.enterprise_roots.enabled to true in
about:config to use the operating system store.)
Chrome / Edge (Windows, macOS, Android): open the downloaded file
and confirm "trust for websites" (they use the OS store).
iOS / iPadOS: the profile downloads, then Settings → General
→ VPN & Device Management installs it, and Settings → General
→ About → Certificate Trust Settings turns it on.
Windows (system store, for Chrome / Edge): import it into "Trusted
Root Certification Authorities" for your user.
Enter your API key
Scan the pairing QR
On the computer running LocaLM, open
Settings → Companion app and point your camera at the QR.
Add localm to your phone
localm runs as an installable app. Add it to your home screen
for a full-screen, app-like experience - then open it any time with one tap.
You can also just continue in the browser.
Add to Home Screen (iPhone / iPad):
Tap the Share button (the square with an up-arrow).
Choose Add to Home Screen, then Add.
Open localm from the new home-screen icon.
To install, open your browser's menu and choose Install app /
Add to Home screen.