1 10

Tom Kay

tomkay

AI & ML interests

None yet

Recent Activity

updated a Space about 8 hours ago

baa-ai/MINT

updated a model 1 day ago

baa-ai/Nemotron-3-Super-120B-A12B-MINT-GGUF

updated a model 1 day ago

baa-ai/Nemotron-3-Super-120B-A12B-MINT-MLX

View all activity

Organizations

liked a model 8 days ago

baa-ai/Qwen3.5-35B-A3B-MINT-15GB-GGUF

35B • Updated 1 day ago • 826 • 1

liked a Space 13 days ago

MINT

🌿

Quantize LLMs to fit a specific memory budget without data

liked a model 19 days ago

baa-ai/Qwen3-30B-A3B-SWAN-5bit-MLX

31B • Updated 1 day ago • 396 • 1

liked 2 models 21 days ago

baa-ai/Qwen3-8B-SWAN-6bit-MLX

8B • Updated 7 days ago • 81 • 1

baa-ai/Qwen3.5-397B-A17B-SWAN-3bit-MLX

396B • Updated 12 days ago • 329 • 1

liked a Space 21 days ago

SAKD: SWAN-Guided Knowledge Distillation

📖

Generate quantization‑ready student models via guided distillation

liked a model 23 days ago

baa-ai/GLM-4.7-Flash-SWAN-4bit-MLX

30B • Updated 1 day ago • 675 • 1

liked 2 Spaces 28 days ago

Sensitivity-Aware Training (SAT)

📄

Train LLMs to be quantization‑ready with sensitivity‑aware methods

SWAN: Data-Free Mixed-Precision Quantization

🦢

Quantize LLMs without data using per‑tensor mixed precision

liked a model about 1 month ago

baa-ai/Qwen3.5-397B-A17B-SWAN-4bit-MLX

396B • Updated 12 days ago • 679 • 3