# Copy to ollama-models.yaml (gitignored). Used when LLM_RUNTIME=ollama.
# name = exact tag for `ollama pull`.
# use: chat — Assistent header select; use: memory — settings memory model.
# Requirement: uncensored (abliterated) + Russian for chat. Empty models: [] → no pull.
# Qwen3-VL tags need Ollama ≥ 0.12.7. Pin :8b-instruct — :latest is Thinking.

models:
  # Recommended (~6.1GB): Qwen3-VL Instruct, vision + RU/EN, abliterated
  - name: huihui_ai/qwen3-vl-abliterated:8b-instruct
    use: chat
    default: true

  # Previous default — still in Assistent chat select
  - name: huihui_ai/qwen2.5-vl-abliterated:7b
    use: chat

  # Vector memory (CPU via num_gpu 0 Modelfile after pull) — not shown in chat select
  - name: nomic-embed-text
    use: memory

  # Presets (setup / up --ollama-preset …):
  # light — huihui_ai/qwen2.5-vl-abliterated:3b   (~3GB)
  # text  — huihui_ai/qwen2.5-abliterate:7b       (~5GB, no vision)
  # big   — huihui_ai/qwen2.5-vl-abliterated:32b  (~21GB)