From 9d58df85f3ad4e090f0d1ba03a5aa5ddf34dee2b Mon Sep 17 00:00:00 2001 From: Jeroen Schweitzer Date: Fri, 7 Aug 2026 14:58:57 +0200 Subject: [PATCH] fix(config): default agent model to gemma4:e2b mistral-nemo-large holds ~9.2 GB of the 11 GB card it shares with Speaches, which starves Whisper and breaks voice transcription. gemma4:e2b holds 1.9 GB and is faster. The deployed stack already overrides this via OLLAMA_AGENT_MODEL; this aligns the default so a deployment without that override does not reintroduce the contention. Co-Authored-By: Claude --- webber-api/.env.example | 2 +- webber-api/CHANGELOG.md | 3 +++ webber-api/src/shared/config.py | 2 +- 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/webber-api/.env.example b/webber-api/.env.example index d9c0560..e50937c 100644 --- a/webber-api/.env.example +++ b/webber-api/.env.example @@ -14,7 +14,7 @@ CORS_ORIGINS=["http://localhost:3000","http://localhost:8080"] # LLM - Ollama (tower-of-joy) OLLAMA_URL=http://192.168.86.149:11434 -OLLAMA_AGENT_MODEL=mistral-nemo-large:latest +OLLAMA_AGENT_MODEL=gemma4:e2b OLLAMA_EMBED_MODEL=nomic-embed-text:latest # Auth - Tatlock integration (optional) diff --git a/webber-api/CHANGELOG.md b/webber-api/CHANGELOG.md index 81e8cc6..6c6af4b 100644 --- a/webber-api/CHANGELOG.md +++ b/webber-api/CHANGELOG.md @@ -7,6 +7,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ## [Unreleased] +### Changed +- Default `OLLAMA_AGENT_MODEL` is now `gemma4:e2b` instead of `mistral-nemo-large:latest`, so a deployment without an explicit override no longer exhausts shared GPU memory + ## [1.0.1] - 2026-07-19 ### Changed diff --git a/webber-api/src/shared/config.py b/webber-api/src/shared/config.py index 3e4abd6..83eea7a 100644 --- a/webber-api/src/shared/config.py +++ b/webber-api/src/shared/config.py @@ -64,7 +64,7 @@ class Settings(BaseSettings): # LLM - Ollama (always hot in VRAM on tower-of-joy) ollama_url: str = "http://192.168.86.149:11434" - ollama_agent_model: str = "mistral-nemo-large:latest" + ollama_agent_model: str = "gemma4:e2b" ollama_embed_model: str = "nomic-embed-text:latest" # Auth - Tatlock integration