O09: Quantization

• Publisher: vLLM
• URL: Primary source
• Published: not stated
• Updated/version date: not established
• Accessed: 2026-10-22
• Type: official runtime documentation, rolling latest
• Verification: opened source, rather than relying on a search excerpt

Supported finding

Quantisation trades numerical precision for lower memory use. Supported methods differ by hardware.

Limits and transfer

The table establishes support, not guaranteed performance or acceptable quality for a particular model.

Use in the session

Mechanism and decision conditions. Retain the qualifications when translating the finding into slide copy. No source establishes Knauf’s savings.