JANG Quantized - GGUF for MLX
Collection
MLX models at full speed, GGUF quality. MiniMax M2.7: 88-95.5% MMLU. Requires MLX Studio. @dealignai • 29 items • Updated • 7
sipuliorava
sipuliorava
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF liked a model 11 days ago
dealignai/DeepSeek-V4-Flash-JANG-CRACK liked a model 12 days ago
DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-ThinkingOrganizations
None yet
upvoted a collection 3 months ago