NousResearch/hermes-agent
Linux NVIDIA local model support fixes
Cluster 120872 · apps/desktop. Data as of
2 open items. Fix attempted, not merged.
The short answer
1open issue
1open PR
3items grouped
- Known?
- Yes. 3 related items grouped here, 0 issues already closed.
- Fix event
- No fix has been merged to main. 1 PR closed without merging; see the attempts below.
- Tracker
- The maintainers' tracker marks this
unresolved. That is separate from the fix event. - Still open
- 1 issue and 1 PR.
Next step: read the attempts below. Your case may extend or revive that work.
Pick up a Lab taskThese items address multiple barriers to using local models on Linux with NVIDIA GPUs, including a missing CUDA asset, a hidden UI pane, and a memory configuration issue affecting 8 GB cards. The work spans both the desktop UI and local runtime layers.
Open issues1
- Issue#120872Local models unusable on Linux + NVIDIA: auto backend resolves to a nonexistent CUDA asset, UI hidden behind --local, and the 64K floor forces spill on 8 GB cards
Open PRs1
- PR#127294fix(desktop): show the local models pane on Linux without --local
1 PR closed without merging
From the close comments: done elsewhere 1
-
#120885 fix(local-runtime): support Linux NVIDIA defaults · done elsewhere →
41cd7b6,3619638,#120872
How this cluster was grouped
-
Link evidence (
structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference. -
Pairwise link density
0.67: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Subsystem
- apps/desktop
- Closed issues
- 0
- Attempts
- 1 PR closed without merging