HarryH

harryherbig

AI & ML interests

None yet

Recent Activity

liked a model 18 days ago

unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit

new activity 18 days ago

unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit:Tested on an M3 Max 36GB: my go-to when speed matters more than perfect regression coverage.

new activity 18 days ago

lmstudio-community/Qwen3.8-27B-MLX-4bit:Tested on an M3 Max 36GB: the only model that still caught its own mistakes when a wrong answer would be expensive

View all activity

Organizations

None yet

New activity in unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit 18 days ago

Tested on an M3 Max 36GB: my go-to when speed matters more than perfect regression coverage.

#6 opened 18 days ago by

New activity in lmstudio-community/Qwen3.8-27B-MLX-4bit 18 days ago

Tested on an M3 Max 36GB: the only model that still caught its own mistakes when a wrong answer would be expensive

#1 opened 18 days ago by