GGUF vs AWQ vs GPTQ vs MLX: Which Quantization to Use
Quantization formats compared with real file sizes and bits per weight. Why Q4 does not halve a model, and why low quants generate faster.
Tag
#vllm
Kimi K3 Weights Are Public: 2.8T Params, 64-GPU Reality
Moonshot released the full Kimi K3 weights on July 27, 2026: 2.8T params, 1M context, MXFP4. Read the license before you plan a deployment.
Open-Source AI Wins: NVIDIA Goes All-In on Open Models, Lightricks Ships 4K Video, and Local Inference Matures
GTC 2026's biggest announcements were open-source. Nemotron 3 Super runs locally on RTX PCs, LTX 2.3 generates 4K video with audio, and vLLM hits production grade.
Open-Source AI Wins: OLMo Hybrid Rewrites Efficiency, Karpathy Ships Research Agents, and Local Tools Level Up
This week's open-source highlights: AI2's hybrid architecture proves transformers need help, autoresearch automates ML experiments overnight, and local inference gets serious upgrades.
Critical vLLM Vulnerability Lets Attackers Take Over AI Servers With a Video Link
A CVSS 9.8 flaw in the popular AI inference engine allows unauthenticated remote code execution through malicious video URLs. Patch now if you're running multimodal models.