Skip to content

Update track-token-usage-local-models.md #54

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Tom-Fynes merged 1 commit into from
Aug 16, 2026
Merged

Update track-token-usage-local-models.md #54

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions blog/2026/track-token-usage-local-models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,7 +168,7 @@ So what does it look like? Here's a screenshot of the dashboard running on my la
<img
src="/blog/2026/static/img/ollama-usage-dashboard.png"
alt="ollama-usage dashboard showing token usage KPIs, a per-tag breakdown table, and tokens-per-second and requests-per-day charts, styled in the Fynes Forge dark theme"
style="width:100%; border-radius:4px; border:1px solid rgba(79,98,114,0.3);"
style={{width: '100%', borderRadius: '4px', border: '1px solid rgba(79,98,114,0.3)'}}
/>

## Does This Actually Track Cline?
Expand Down Expand Up @@ -224,4 +224,4 @@ Full source is in the repo — worth a read there rather than as a wall of code

## The Actual Point

None of this is about cost. It's about the fact that "no bill" doesn't mean "no resource." Context window, thermal headroom, and comparative model performance are all real constraints on this hardware, and every one of them is sitting in the response body Ollama already sends back — mostly unread, until you decide to log it.
None of this is about cost. It's about the fact that "no bill" doesn't mean "no resource." Context window, thermal headroom, and comparative model performance are all real constraints on this hardware, and every one of them is sitting in the response body Ollama already sends back — mostly unread, until you decide to log it.
Loading