TurboQuant 4-bit mlx-lm models. TriAttention compatible. PR #1 merged MIT+NVIDIA.
-
deadbydawn101/gemma-4-E4B-mlx-4bit
Image-Text-to-Text • 2B • Updated • 4.08k • 6 -
deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit
Text Generation • Updated • 14.3k • 18 -
deadbydawn101/gemma-4-E2B-Heretic-Uncensored-mlx-4bit
Image-Text-to-Text • 1B • Updated • 9.11k • 13 -
deadbydawn101/gemma-4-21b-REAP-Tool-Calling-mlx-4bit
Image-Text-to-Text • 4B • Updated • 2.58k • 4