Launching Monday, December 21, 2026
00
:00
:00
:00
days
hours
mins
secs
About
quantized.uk is a free, no-signup web toolkit for planning local quantized LLM runs. Estimate model weights and KV-cache memory from a model, quantization format, context length and hardware details, then compare the estimate with your GPU or Mac. Browse model and GPU references, compare models and formats, read guides, and generate commands for llama.cpp, Ollama, vLLM or ExLlamaV2. Available in English and Chinese. These are planning estimates, not guarantees; verify on your hardware.
