Cairn
NousResearch/hermes-agent

Hermes with Ollama/custom providers: gemma4 failures and token limits

Cluster 39281 · agent. Data as of

2 open items. Fix merged in #41694 on 8 Jun 2026. Check it covers your case.

The short answer

1open issue
1open PR
8items grouped
Known?
Yes. 8 related items grouped here, 3 issues already closed.
Fix event
A fix was merged to main in PR #41694. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this partially resolved, deciding PR #41694. That is separate from the fix event.
Still open
1 issue and 1 PR.

Most members concern Hermes running against Ollama or custom OpenAI-compatible providers, covering gemma4 bug reports, output truncation, large context requests, and several PRs proposing different default max_tokens values. One PR about resolving custom:<name> slugs is related to custom provider handling but is less clearly tied to the same issue.

Open issues1

  • Issue#46833[Setup]: Thinking models on `custom`/Ollama (OpenAI-compatible) providers always truncate, and Hermes requests the full GGUF context window causing VRAM blowups

Open PRs1

  • PR#45930Fix false local Ollama length truncation

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #41694 fix(ollama): set default_max_tokens=65536 for custom/Ollama provider

    merged to main

    files: plugins/model-providers/custom/__init__.py, scripts/release.py

2 PRs closed without merging

From the close comments: done elsewhere 1 · merged via another change 1

  • #39624 fix(ollama): set default_max_tokens=4096 for custom/Ollama provider · merged via another change → 09ec26c, #41694
  • #64426 fix(providers): resolve custom:<name> slug to custom profile for wire path (#39281) · done elsewhere → c88723d, #39281, #41694
Closed issues · 3
  • Closed#39281[Bug]: Hermes fails to work using gemma4 with ollama backend
  • Closed#45924[Bug]: hermes + gemma 4 12b
  • Closed#49297[Bug]: Hermes fails to work using gemma4 with ollama backend
How this cluster was grouped
  • Link evidence (partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
  • Members outside that structural core may belong to a different underlying problem.
  • Pairwise link density 0.19: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means 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 Lab

At a glance

Subsystem
agent
Merged PRs
#41694
Closed issues
3
Attempts
2 PRs closed without merging
Fix link checked
8 Jun 2026

For your agent

The same facts, typed.

cluster/39281.json
cluster/39281.md