FOXAI SEARCH
Search FoxAI
AI Models 85021
- BiomedCLIP-vit-bert-hf↗
chuhac
- humanizer-12b-mlx-8bit↗
cowWhySo
- MiniMax-M2.7-AWQ-4bit↗
cyankiwi
- WikiQwen-35B-A3B↗
devon7y
- Qwen3.8-27B-GGUF↗
DhruvalLabs
> [!IMPORTANT] > **This VLM requires TWO files** — a text backbone GGUF and the `mmproj` vision encoder GGUF. > Download one text backbone (e.g. Q4_K_M) **and** the mmproj file. Both must be in the same folder. 1. Search for `DhruvalLabs/Qwen3.8-27B` in LM Studio 2. Download the Q4_K_M text file **and** the mmproj file 3. Load the model — LM Studio automatically uses both files > **Why is mmproj always F16?** > The vision encoder maps image pixels to token embeddings. Quantizing it causes > visible visual artifacts and degraded image understanding. It stays at F16 (half precision) > which is already very efficient at ~1-2GB for most models.
- Qwen2.5-32B-Instruct-AWQ-INT4↗
drawais
- gemma-4-31B-it-4bit-W4A16-AWQ↗
ebircak
- layerskip-llama2-7B↗
facebook
- mms-tts-cym↗
facebook
- mms-tts-hil↗
facebook
