TokenAssemble

About

TokenAssemble helps you determine which local large language models your existing GPU, Mac, or mini-PC can support prior to downloading a model or purchasing new hardware. It assesses compatibility factors such as VRAM or unified memory capacity, quantization levels, context length, anticipated performance speed, and runtime suitability. Based on this analysis, it provides a clear decision and a suggested configuration for platforms including Ollama, LM Studio, llama.cpp, and vLLM.