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 20 days ago

KV Cache Quantization - what is the default precision

1

#2 opened 20 days ago by

deepmage121

updated 2 models 21 days ago

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

Updated 17 days ago • 303

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

Text Generation • Updated 5 days ago • 139

updated a model 22 days ago

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

Text Generation • Updated 22 days ago • 387 • 2