Dan Alistarh

Explore new open source quantized reasoning models based on the DeepSeek-R1-Distill suite that deliver near-perfect accuracy and inference speed improvements.

Discover Sparse Llama: A 50% pruned, GPU-optimized Llama 3.1 model with 2:4 sparsity, enabling faster, cost-effective inference without sacrificing accuracy.

Advancing AI efficiency is more critical than ever, and sparsity has proven to be a cornerstone in this pursuit.

Quantized LLMs achieve near-full accuracy with minimal trade-offs after 500K+ evaluations, providing efficient, high-performance solutions for AI model deployment.

4-bit and 8-bit quantized LLMs excel in long-context tasks, retaining over 99% accuracy across 4K to 64K sequence lengths.