Show HN: An immutable local inference appliance with routing capability
Hey HN I’ve been working on a little side project after spending a bunch of time customising my inference stack at home. I figured it’d be nice to have something relatively portable, easily maintainable and configurable through a UI. It’s early days, there is built support for Vulkan, HIP and CUDA but I’ve only really tested it on AMD (that’s what I’ve got). So more hardware exposure would be awesome along with feedback and the like. At the moment there is no commercial model. Just wanting to ge
Read original source
Source record
Recorded metrics
points · 1 votes
2026-11-08 05:15:12.370Z
cumulative since publication
Research analysis
Project record
Repository: diffsec/sibyl. Source account: Hey HN I’ve been working on a little side project after spending a bunch of time customising my inference stack at home. I figured it’d be nice to have something relatively portable, easily maintainable and configurable through a UI. It’s early days, there is built support for Vulkan, HIP and CUDA but I’ve only really tested it on AMD (that’s what I’ve got). So more hardware exposure would be awesome along with feedback and the like. At the moment there is no commercial model. Just wanting to ge
Observed adoption & comparisons
Source votes: 1 votes (Nov 8, 2026 UTC; cumulative since publication) Recent records to compare: “Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU” (Show HN, Nov 8, 2026); “Show HN: LLM weight editing tool made by a 15-year-old” (Show HN, Nov 8, 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.