Punishing Four Local Models With a 10,000-Word Great Lakes Feature
Four local models face a 10,000-word Great Lakes writing and revision test. One survives the length; none survives release review.
-
-
Benchmark Artifact: Qwen3.8 Flash Next Sushi 3bpw — Freshwater Graves
Qwen3.8 Flash Next Sushi 3bpw’s preserved, clearly warned Great Lakes long-form benchmark artifact and measured results.
-
Benchmark Artifact: Ornith 1.5 35B — Freshwater Graves
Ornith 1.5 35B’s preserved, clearly warned Great Lakes long-form benchmark artifact and measured results.
-
Benchmark Artifact: Gemma 4 31B MLX — Freshwater Graves
Gemma 4 31B MLX’s preserved, clearly warned Great Lakes long-form benchmark artifact and measured results.
-
Benchmark Failure: Qwen3.8 27B MLX — Freshwater Graves
A preserved failure artifact from the 10,000-word Great Lakes endurance test of qwen3.8:27b-mlx.
