LLM

Language models on hardware you already own. Quantization trade-offs, context length limits, and token rates measured with the conditions attached.

1 article

Articles

Official source LLMVerified Aug 29, 2026GLM-5.3-Flash open weights: what the model card says, and what it means for a 12GB cardA 320B parameter multimodal MoE released under MIT. What the model card states, and why a 12GB card is the wrong first question to ask about it.