Alexandre Marques

alexmarques's activity

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

updated a model 24 days ago

nm-testing/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic

Text Generation • Updated 22 days ago • 944 • 3

New activity in neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16 3 months ago

KV Cache Quantization - what is the default precision

1

#2 opened 3 months ago by

deepmage121

updated 18 models 3 months ago

neuralmagic/Qwen2.5-0.5B-Instruct-quantized.w8a8

Text Generation • Updated Dec 9, 2024 • 18

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

Updated Dec 8, 2024 • 11

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

Text Generation • Updated Dec 19, 2024 • 58 • 1

neuralmagic/Qwen2.5-72B-FP8-dynamic

Text Generation • Updated Dec 3, 2024 • 40

neuralmagic/Qwen2.5-72B-quantized.w8a8

Text Generation • Updated Dec 3, 2024 • 45

neuralmagic/Qwen2.5-14B-quantized.w8a8

Text Generation • Updated Dec 3, 2024 • 55

neuralmagic/Qwen2.5-14B-FP8-dynamic

Text Generation • Updated Dec 3, 2024 • 91

neuralmagic/Qwen2.5-7B-quantized.w8a8

Text Generation • Updated Dec 3, 2024 • 59

neuralmagic/Qwen2.5-7B-FP8-dynamic

Text Generation • Updated Dec 3, 2024 • 53

neuralmagic/Qwen2.5-3B-FP8-dynamic

Text Generation • Updated Dec 3, 2024 • 55

neuralmagic/Qwen2.5-1.5B-FP8-dynamic

Text Generation • Updated Dec 3, 2024 • 40

neuralmagic/Qwen2.5-0.5B-FP8-dynamic

Text Generation • Updated Dec 3, 2024 • 62

neuralmagic/Qwen2.5-3B-quantized.w8a8

Text Generation • Updated Dec 3, 2024 • 28

neuralmagic/Qwen2.5-1.5B-quantized.w8a8

Text Generation • Updated Dec 3, 2024 • 23

neuralmagic/Qwen2.5-0.5B-quantized.w8a8

Text Generation • Updated Dec 3, 2024 • 15

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

Text Generation • Updated Dec 3, 2024 • 135 • 2

neuralmagic/Qwen2.5-14B-quantized.w8a8

Text Generation • Updated Dec 3, 2024 • 55

neuralmagic/Qwen2.5-14B-FP8-dynamic

Text Generation • Updated Dec 3, 2024 • 91