AI Briefing#llm-compression
The latest AI and developer news about #llm-compression, with the original source and a short summary.
The latest AI and developer news about #llm-compression, with the original source and a short summary.
The framework compresses Nemotron 3.5 Super from 120B to 74B parameters while retaining 95% of its mean benchmark score.
The expert-pruned build retains 98.7% of LiveCodeBench v6 performance while reducing transformer weights to 72.1 GB.
The new STQ1_0 format achieves 1.3125 bits per weight, reducing the model's storage footprint from roughly 1.5TB while maintaining performance comparable to IQ1_M.
The official implementation supports compression down to 0.1 bits per weight across models including Llama 3, Phi-4, and Qwen3.
A new implementation of NanoQuant, which can compress transformer models to sub-1-bit, has been released.