Quinn 3.8
A medium-scale open-source large language model with 27B parameters that supports quantized execution on consumer-grade hardware.
Timeline (last 90 days)
Simon Willison used the Quinn 3.8 (27B-parameter) model on a laptop and, reading only the raw weights without external tools, successfully identified three games—Pac-Man, Pong and Breakout—taking about an hour of inference per game.
In Simon Willison's pure-reading test, the Quinn 3.8 model failed on the fourth game.
Quinn 3.8 is a medium-scale open-source large language model with 27B parameters that can run in quantized form on consumer laptops with sufficient VRAM.
All Facts (3)
Simon Willison used the Quinn 3.8 (27B-parameter) model on a laptop and, reading only the raw weights without external tools, successfully identified three games—Pac-Man, Pong and Breakout—taking about an hour of inference per game.
50%UnverifiedIn Simon Willison's pure-reading test, the Quinn 3.8 model failed on the fourth game.
50%UnverifiedQuinn 3.8 is a medium-scale open-source large language model with 27B parameters that can run in quantized form on consumer laptops with sufficient VRAM.
50%