Quartet: Native FP4 Training Can Be Optimal for Large Language Models Paper • 2505.14669 • Published 8 days ago • 70
RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8 Image-Text-to-Text • Updated 9 days ago • 100 • 1
RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8 Image-Text-to-Text • Updated 9 days ago • 9.09k • 4
RedHatAI/Mistral-Small-24B-Instruct-2501-FP8-dynamic Text Generation • Updated 9 days ago • 221k • 13