Alkd

Alkd

·

AI & ML interests

None yet

Recent Activity

liked a model about 1 month ago

Qwen/Qwen3.8-27B

updated a model 4 months ago

Alkd/TEA-ASR-1.1-MLX-4bit

published a model 4 months ago

Alkd/TEA-ASR-1.1-MLX-4bit

View all activity

Organizations

None yet

New activity in mlx-community/gemma-4-e2b-4bit 7 months ago

⚠️ Existing MLX quantized Gemma 4 models (mlx-community, unsloth) produce garbage output due to quantizing PLE (Per-Layer Embedding) layers.

#1 opened 7 months ago by