MLX format at float16 for M1/M2 Silicon
Harish Kothandaraman
hsk0201
·
AI & ML interests
None yet
Recent Activity
upvoted a collection about 14 hours ago
Qwen3.6-35B-A3B new activity 3 days ago
mlx-community/Qwen3.6-27B-OptiQ-4bit:Adding the kv_config.json to the repo updated a model 22 days ago
hsk0201/Qwen3.6-27B-oQ4-mtpOrganizations
None yet