Tom Kay

tomkay

·

AI & ML interests

None yet

Recent Activity

updated a model 1 day ago

baa-ai/Kolibri-1-RAM-50GB-MLX

published a model 2 days ago

baa-ai/Kolibri-1-RAM-50GB-MLX

upvoted a paper 7 days ago

Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution

View all activity

Organizations

upvoted a paper 7 days ago

Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution

Paper • 2607.28196 • Published Jul 30 • 2

upvoted a paper 3 months ago

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 48

upvoted a collection 5 months ago

Qwen3.5-35B-A3B

Mixed-precision MLX builds of Qwen/Qwen3.5-35B-A3B for Apple Silicon, quantized by baa.ai. Size points: 12.5-21, 25, 29, 31 GB. • 9 items • Updated 11 days ago • 1

upvoted a collection 6 months ago

Qwen3.5-122B-A10B

MINT quantized versions of Qwen3.5-122B-A10B at multiple budget targets (MLX & GGUF) • 3 items • Updated 11 days ago • 2