Skip to content

Update AI-hosting model catalog: add GLM/Qwen/Mistral entries with corrected IDs and capabilities, remove Devstral-small-2-24B #37

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
LukasFritzeDev merged 6 commits into from
Jun 17, 2026
Merged

Update AI-hosting model catalog: add GLM/Qwen/Mistral entries with corrected IDs and capabilities, remove Devstral-small-2-24B #37

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
afab76e
Initial plan
Copilot Jun 3, 2026
51806bf
fix: update mittwald model metadata for latest AI-hosting models
Copilot Jun 3, 2026
59d3489
fix: treat Qwen reranker as non-chat model
Copilot Jun 3, 2026
c3e97db
fix: use GLM-OCR model identifier
Copilot Jun 3, 2026
596abc8
fix: align model IDs and capabilities with docs
Copilot Jun 16, 2026
03b4d88
fix: PHP fatal error
LukasFritzeDev Jun 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,9 +72,10 @@ Fully supported for conversational AI, content generation, and chat-based intera

**Available Models:**
- **GPT-OSS models**: Open-source GPT-compatible models
- **Qwen**: Qwen 3.5 122B-FP8 and Qwen 3.6 35B-FP8 (supports vision/image input)
- **Qwen**: Qwen 3.5 122B-FP8 and Qwen 3.6 35B-FP8 (supports vision/image input), Qwen3-VL-Reranker, Qwen3.6-0.8B
- **Ministral**: supports vision/image input
- **Devstral**: optimized for code generation
- **Mistral Medium 3.5**
- **GLM OCR**: `zai-org/GLM-OCR`

- **Capabilities:**
- Standard text chat
Expand Down
5 changes: 4 additions & 1 deletion includes/MittwaldModelMetadataDirectory.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,14 +108,17 @@ static function ( array $modelData ) use (
switch ( $modelId ) {
case 'gpt-oss-120b':
case 'Qwen3-Coder-30B-Instruct':
case 'Devstral-Small-2-24B-Instruct-2512':
case 'Mistral-Medium-3.5':
Comment thread
LukasFritzeDev marked this conversation as resolved.
Outdated
Comment thread
LukasFritzeDev marked this conversation as resolved.
Outdated
case 'Qwen3.6-0.8B':
Comment thread
LukasFritzeDev marked this conversation as resolved.
Outdated
$modelCaps = $gptCapabilities;
$modelOptions = $gptOptions;
break;
case 'Mistral-Small-3.2-24B-Instruct':
case 'Ministral-3-14B-Instruct-2512':
case 'Qwen3.5-122B-A10B-FP8':
case 'Qwen3.6-35B-A3B-FP8':
case 'Qwen3-VL-Reranker':
Comment thread
LukasFritzeDev marked this conversation as resolved.
Outdated
case 'zai-org/GLM-OCR':
Comment thread
LukasFritzeDev marked this conversation as resolved.
Outdated
$modelCaps = $gptCapabilities;
$modelOptions = $gptMultimodalInputOptions;
break;
Expand Down
5 changes: 3 additions & 2 deletions readme.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,9 +24,10 @@ Fully supported for conversational AI, content generation, and chat-based intera

**Available Models:**
- **GPT-OSS models**: Open-source GPT-compatible models
- **Qwen**: Qwen 3.5 122B-FP8 and Qwen 3.6 35B-FP8 (supports vision/image input)
- **Qwen**: Qwen 3.5 122B-FP8 and Qwen 3.6 35B-FP8 (supports vision/image input), Qwen3-VL-Reranker, Qwen3.6-0.8B
- **Ministral**: supports vision/image input
- **Devstral**: optimized for code generation
- **Mistral Medium 3.5**
- **GLM OCR**: `zai-org/GLM-OCR`

**Capabilities:**
- Standard text chat
Expand Down