Alexander Matveev's picture

1 1

Alexander Matveev

alexm-nm

·

http://www.neuralmagic.com

alexm-nm

AI & ML interests

AI performance

Recent Activity

upvoted a paper about 2 months ago

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

View all activity

Organizations

models 8

alexm-nm/tinyllama-24-gptq-8bit-channelwise

Text Generation • Updated May 8 • 277

alexm-nm/tinyllama-24-marlin24-8bit-channelwise

Text Generation • Updated May 8 • 472 • 1

alexm-nm/tinyllama-24-gptq-8bit-g128

Text Generation • Updated May 8 • 3.36k

alexm-nm/tinyllama-24-marlin24-8bit-g128

Text Generation • Updated May 8 • 5.16k • 1

alexm-nm/tinyllama-24-gptq-4bit-channelwise

Text Generation • Updated May 8 • 278

alexm-nm/tinyllama-24-marlin24-4bit-channelwise

Text Generation • Updated May 8 • 469 • 1

alexm-nm/tinyllama-24-gptq-4bit-g128

Text Generation • Updated May 8 • 3.36k

alexm-nm/tinyllama-24-marlin24-4bit-g128

Text Generation • Updated May 8 • 13k • 1

datasets

None public yet