MLX models at full speed, GGUF quality. MiniMax M2.7: 88-95.5% MMLU. Requires MLX Studio. @dealignai
Jinho Jang
jangq
AI & ML interests
JANG_Quantization - GGUF for MLX!
Recent Activity
updated a collection about 19 hours ago
Custom Calibrated: Kimi - GLM - MiniMax updated a model 2 days ago
JANGQ-AI/Holo3-35B-A3B-JANGTQ4 updated a model 2 days ago
JANGQ-AI/Holo3-35B-A3B-JANGTQ2Organizations
models 0
None public yet
datasets 0
None public yet