v1.0.11 – Qwen3.6 Support and GGUF Discovery Improvements
This release adds Qwen3.6 local GGUF support and improves GGUF model discovery for users who store models outside the default ComfyUI models directory.
Added
- Added support for Qwen3.6 local GGUF models
- Detects
qwen36andqwen3.6model filenames - Routes Qwen3.6 through the existing
Qwen35ChatHandlerpath - Updates Qwen3.5/3.6 mmproj requirement messages and logging
- Detects
Improved
-
Improved local GGUF model discovery
- Models registered through ComfyUI
extra_model_paths.yamlare now discovered - External model paths, including paths on another drive, are preserved as absolute paths
- Thanks to @bongobongo2020 for this contribution
- Models registered through ComfyUI
-
Improved mmproj auto-detection
- If no family-prefixed mmproj matches but the model directory contains exactly one
mmproj-*.gguf, that file is now selected automatically - Ambiguous cases with multiple unmatched mmproj files still require manual selection
- Thanks to @bongobongo2020 for this contribution
- If no family-prefixed mmproj matches but the model directory contains exactly one
Documentation
- Updated README and CHANGELOG for v1.0.11