Bonsai 2 27B: How Ternary Weights and a Hadamard Rotation Compress a 27B Model to 5.9 GB
Bonsai 2 27B: How Ternary Weights and a Hadamard Rotation Compress a 27B Model to 5.9 GB A 27-billion-parameter model that fits in under 6 GB and retains 98.2% of its full-precision benchmark performance sounds like a contradiction. Bonsai 2 27B, released by PrismML on September 17, 2026, makes tha…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-09-28 16:07 · DEV Community — Machine Learning
Bonsai 2 27B: How Ternary Weights and a Hadamard Rotation Compress a 27B Model to 5.9 GB