diff --git a/blog/2026/track-token-usage-local-models.md b/blog/2026/track-token-usage-local-models.md index 4f68b9a..3c86159 100644 --- a/blog/2026/track-token-usage-local-models.md +++ b/blog/2026/track-token-usage-local-models.md @@ -168,7 +168,7 @@ So what does it look like? Here's a screenshot of the dashboard running on my la 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 ## Does This Actually Track Cline? @@ -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. \ No newline at end of file +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.