mistralai/Magistral-Small-2509-GGUF
24B
•
Updated
•
1.67k
•
67
Note
Modern, supports vision and thinking - Q4_K_M with 8K context or IQ4_XS for 16K
Text Generation
•
22B
•
Updated
•
5.96M
•
•
4.3k
Note
Beast for some tasks - use high thinking
nunchaku-ai/nunchaku-flux.1-krea-dev
Text-to-Image
•
Updated
•
7.34k
•
118
Note
Realistic text to image
nunchaku-ai/nunchaku-flux.1-kontext-dev
Image-to-Image
•
Updated
•
12.2k
•
64
Note
Great image editing
unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF
31B
•
Updated
•
21.2k
•
287
Note
Very fast and reliable, good speed even with offloading as its an MOE
moondream/moondream3-preview
Image-Text-to-Text
•
9B
•
Updated
•
9.78k
•
554
Note
goated for Vision
Text-to-Speech
•
Updated
•
554k
•
•
1.46k
Note
Great TTS , supports voice cloning
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text
•
27B
•
Updated
•
8.47k
•
378
Note
All round great . Doesn't fit fully so it will be slow, use it for one off tasks
noctrex/Qwen3-Coder-REAP-25B-A3B-MXFP4_MOE-GGUF
Text Generation
•
25B
•
Updated
•
2.63k
•
14