Qwen3.8 27B sums big numbers in words, hitting 167/169 with reasoning on
AI summary
Simon Willison re-ran an experiment Colin Frasier first tried two years ago with GPT-4o: have a model compute large sums but return the answer in words. He ran it on local hardware (a DGX Spark), using a Codex Remote session (GPT-6 Astra) to write and execute the test with Qwen3.8-27B-Q4_K_M.gguf. With reasoning disabled he sampled 30 attempts per cell; with reasoning enabled each run took so long that he used one sample per pair, and the model got 167 of 169 attempts right.
In-depth insight
Digit-by-digit addition in prose is often treated as a stress test of model arithmetic, and the result suggests a local 27B-class model can handle it fairly reliably once reasoning is enabled.