Alexandre Marques

alexmarques's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 about 1 month ago

KV Cache Quantization - what is the default precision

1

#2 opened about 1 month ago by

deepmage121

updated 3 models about 1 month ago

nm-testing/llama-3-fp8-2of4-dynamic-uncompressed

Updated Dec 8, 2024 • 84

neuralmagic/Sparse-Llama-3.1-8B-gsm8k-2of4-FP8-dynamic

Text Generation • Updated 22 days ago • 123 • 1

neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w8a8

Text Generation • Updated Dec 3, 2024 • 411 • 2