Ronsiek's picture

Ronsiek

warrenronsiek

·

https://www.warren-r.com

warrenronsiek

AI & ML interests

None yet

Recent Activity

new activity 1 day ago

mlx-community/gemma-4-e2b-4bit:⚠️ Existing MLX quantized Gemma 4 models (mlx-community, unsloth) produce garbage output due to quantizing PLE (Per-Layer Embedding) layers.

liked a model 12 days ago

Qwen/Qwen3-Reranker-0.6B

liked a model 12 days ago

Qwen/Qwen3-Embedding-0.6B

View all activity

Organizations

warrenronsiek 's models

None public yet