This collection includes anything that is new, experimental, and/or untested.
🔄 In a Training Loop
BennyDaBall
BennyDaBall
AI & ML interests
Finetuning & quantization
Recent Activity
updated a model 1 day ago
BennyDaBall/Mistral-44B-MoE-Patched-MLX-4bit-G64 updated a model 1 day ago
BennyDaBall/gemma-3-27b-tools-mlx-4bit updated a model 1 day ago
BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUFOrganizations
None yet
Various miscellaneous text, video, image, and audio model quants, tuned by BennyDaBall
-
BennyDaBall/Qwen-Image-2.1-Turbo-NVFP4
Text-to-Image • Updated • 6.87k • 4 -
BennyDaBall/Qwen-Image-2.1-NVFP4
Text-to-Image • Updated • 46.9k • 19 -
BennyDaBall/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-NVFP4
Image-Text-to-Text • 27B • Updated • 1.32k • 4 -
BennyDaBall/Qwopus3.8-27B-Flash-NVFP4
Image-Text-to-Text • 27B • Updated • 468 • 3
This collection includes anything that is new, experimental, and/or untested.
Various miscellaneous text, video, image, and audio model quants, tuned by BennyDaBall
-
BennyDaBall/Qwen-Image-2.1-Turbo-NVFP4
Text-to-Image • Updated • 6.87k • 4 -
BennyDaBall/Qwen-Image-2.1-NVFP4
Text-to-Image • Updated • 46.9k • 19 -
BennyDaBall/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-NVFP4
Image-Text-to-Text • 27B • Updated • 1.32k • 4 -
BennyDaBall/Qwopus3.8-27B-Flash-NVFP4
Image-Text-to-Text • 27B • Updated • 468 • 3
models 30
BennyDaBall/EmbeddingGemma-2-NVFP4-GGUF
Feature Extraction • 0.3B • Updated • 1.11k
BennyDaBall/Qwen-Image-2.1-Turbo-NVFP4
Text-to-Image • Updated • 6.87k • 4
BennyDaBall/Qwen-Image-2.1-NVFP4
Text-to-Image • Updated • 46.9k • 19
BennyDaBall/Mistral-44B-MoE-Patched-MLX-4bit-G64
Text Generation • 44B • Updated • 129
BennyDaBall/gemma-3-27b-tools-mlx-4bit
Updated • 99
BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF
Text Generation • 139B • Updated • 108 • 5
BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4
Text Generation • 139B • Updated • 306 • 4
BennyDaBall/Qwopus3.8-27B-Flash-EXL3
Image-Text-to-Text • Updated • 8 • 4
BennyDaBall/Qwopus3.8-27B-Flash-NVFP4
Image-Text-to-Text • 27B • Updated • 468 • 3
BennyDaBall/Qwen3.8-Uncensored-NVFP4-MTP
Text Generation • 0.5B • Updated • 1.72k • 12
datasets 0
None public yet