Open
Conversation
- New /dashboard route showing GPU devices, loaded models, and system info - Proxy /api/ps through app UI server for running model data - Dashboard link in sidebar and Windows system tray menu - Auto-refreshing model list (5s polling via React Query) - GPU card shows VRAM, library, compute capability, driver version - Model cards show VRAM usage bar, context length, parameters, expiry
…dling - Add description (GPU model name), available (free VRAM), and type (discrete/iGPU) fields to InferenceCompute struct across backend and frontend - Parse additional fields from inference compute log lines - Show GPU description as card title with discrete/iGPU badge - Add VRAM usage progress bar with color-coded thresholds - Fix formatBytes crash on negative/NaN values - Clamp model VRAM percentage to max 100% - Add error states for failed GPU and model queries - Fix ProcessModelResponse type to include parent_model field - Use InferenceCompute from gotypes instead of inline type
This was referenced Mar 1, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
/dashboardpage to the Ollama desktop app showing real-time GPU and model monitoring info/api/psendpoint through the app UI server for running model dataRelated PRs
This is Part 2 of 3 in the Ollama Desktop UI improvement series:
Each PR is independent and can be merged separately. Together they transform the desktop app from a chat-only interface into a comprehensive Ollama management tool with full settings control, real-time monitoring, and model lifecycle management.
Changes
ui.go/api/psendpointDashboard.tsxapi.tsgetRunningModels()API function +ProcessModelResponsetypesdashboard.tsxChatSidebar.tsxmenus.go,messages.go,eventloop.goFeatures
Test plan
cd app/ui/app && npm run buildnpx tsc --noEmit