Google Research unveiled TurboQuant, a novel quantization algorithm that compresses large language models’ Key-Value caches ...

NVIDIA showcases Neural Texture Compression at GTC 2026, cutting VRAM usage by up to 85% with real-time AI reconstruction.

Intel and Nvidia show off how textures -- which take up a large chunk of PC games -- could be compressed to save you money ...

What Google's TurboQuant can and can't do for AI's spiraling cost ...

Microsoft's AI-driven CapEx is translating rapidly into revenue and free cash flow. Find out why MSFT stock is upgraded to ...

Artificial intelligence model compression startup Refiant AI said today it has raised $5 million in seed funding from VoLo Earth Ventures to try to put an end to the “arms race” that has ignited a ...

A new compression technique from Google Research threatens to shrink the memory footprint of large AI models so dramatically ...

Google's TurboQuant combines PolarQuant with Quantized Johnson-Lindenstrauss correction to shrink memory use, raising ...

As global technology giants prepare to spend nearly $700 billion this year building data centres to power artificial ...

Sandisk stock fell ~7% after Google TurboQuant, but compression applies only to KV cache, not total storage demand. Learn why SNDK stock is upgraded to strong buy.

Within 24 hours of the release, community members began porting the algorithm to popular local AI libraries like MLX for Apple Silicon and llama.cpp.