Show HN: Tokspur a 3x faster open source inference engine for Macs
While we were trying to solve a separate problem, we ended up on a bit of a side quest and built an inference engine. We got ourselves some nice, shiny new Mac M5 Max 128GB machines while doing a lot of local LLM work for another project and ended up wanting to run some bigger models. When we were running models for coding, we noticed a few improvements that we might be able to make around repetition between turns. After that, the whole thing got a little out of hand, and we ended up writing our
Read original source
Source record
Recorded metrics
points · 3 votes
2026-11-10 13:00:31.075Z
cumulative since publication
Research analysis
Project record
Repository: san-digital/tokspur. Source account: While we were trying to solve a separate problem, we ended up on a bit of a side quest and built an inference engine. We got ourselves some nice, shiny new Mac M5 Max 128GB machines while doing a lot of local LLM work for another project and ended up wanting to run some bigger models. When we were running models for coding, we noticed a few improvements that we might be able to make around repetition between turns. After that, the whole thing got a little out of hand, and we ended up writing our
Observed adoption & comparisons
Source votes: 3 votes (Nov 10, 2026 UTC; cumulative since publication) Recent records to compare: “anthropics/claude-quickstarts” (GitHub Trending, Nov 10, 2026); “Show HN: Qitt – A proactive AI chief of staff built on T3 Code” (Show HN, Nov 10, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.