Conway Research Squeezes Saluki's 27B Model Into 8 GB and Beats the Original

A 7.89 GB IQ2 quant of Qwen3.8-27B that beats the full 54 GB model on tool-calling benchmarks while fitting on consumer GPUs.

Source

AlphaSignal

Published

Oct 10, 2026, 9:28 AM

Author

AlphaSignal Newsroom

Read

1 min read

A 7.89 GB IQ2 quant of Qwen3.8-27B that beats the full 54 GB model on tool-calling benchmarks while fitting on consumer GPUs.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Next reads