# NousResearch/hermes-agent · Hermes with Ollama/custom providers: gemma4 failures and token limits

## Open now

- 1 issue, 1 PR open on GitHub.
- #46833: \[Setup\]: Thinking models on \`custom\`/Ollama (OpenAI-compatible) providers always truncate, and Hermes requests the full GGUF context window causing VRAM blowups
- PR #45930: Fix false local Ollama length truncation

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.

## TL;DR

- 8 member(s): 1 open issue(s), 3 closed issue(s), 1 open PR(s), 1 merged PR(s), 2 PR(s) closed without merging.
- A fix was merged to main in PR #41694. Verify it addresses your case.
- **Recommended:** read PR #41694 (and any competing PRs below) before filing. Confirm the merged change covers your symptom.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `partially_resolved` · deciding PR(s): `pr-41694`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 member 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.

## Open related issues

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

## Closed / duplicate issues

- #39281: \[Bug\]: Hermes fails to work using gemma4 with ollama backend
- #45924: \[Bug\]: hermes + gemma 4 12b
- #49297: \[Bug\]: Hermes fails to work using gemma4 with ollama backend

## Prior & competing PRs

- **#41694: fix(ollama): set default_max_tokens=65536 for custom/Ollama provider**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `plugins/model-providers/custom/__init__.py`, `scripts/release.py`
- **#39624: fix(ollama): set default_max_tokens=4096 for custom/Ollama provider**. closed without merge
  - maintainer direction: category `merged_via`; implication `superseded`; refs `09ec26c66`, `#41694`
- **#45930: Fix false local Ollama length truncation**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `00a8252b7`
  - files: `agent/conversation_loop.py`, `run_agent.py`, `tests/run_agent/test_run_agent.py`
- **#64426: fix(providers): resolve custom:<name> slug to custom profile for wire path (#39281)**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`; refs `c88723d34a130c82a7eb7b0adb749267643d54f1`, `#39281`, `#41694`

## Fix status

- Merged to main in PR #41694 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-06-08`.
- Subsystem: `agent`