Local AI Glossary
What is EXL2?
Source: local-llm.net/glossary
A quantization format used by ExLlamaV2 that supports variable bitrate across model layers. EXL2 assigns more bits to important layers and fewer to less important ones, achieving better quality at the same average bit rate compared to uniform quantization methods. NVIDIA GPU only.
How EXL2 fits in the local AI stack
EXL2 is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.
See also
- Full Local AI Glossary
- All learn topics
- What is Local AI?
- Quantization explained
- Hardware requirements
- How to choose a local LLM