Published deployment reference, not a 27B or BitShovel inference test
Small-model files, runtime memory and current software →
The 9B card lists a minimum 2.00GB language file and a default PQ2_0 pack of 2.42GB.
PrismML · Released 2026-09-17
Ternary Bonsai 2 27B
The earlier 27B Bonsai 2 model derives from Qwen3.8-27B. Keep its specifications and tests separate from the later Qwen3.5-based models. These ternary weights do not inherit backbone scores; no matching AA/Pi result, and Physics video continuation does not apply.
Original model explanation ↗No comparable leaderboard score is included yet. Explore the evaluations and examples below.
Evaluations: conditions and results
Original model card; retention claims do not generalize to other sizes
27B: backbone, files and evaluation scope ↗
Original release, distinct from October 15’s smaller models
The original September 17 release ↗
PrismML model evolution
- Ternary Bonsai 2 27B
The ternary model derived from Qwen3.8-27B launches under Apache 2.0; file size and vendor retention figures are distinct from device testing.
Original release ↗ - Ternary Bonsai 2 2B / 4B / 9B
Three smaller Qwen3.5-derived models join the family with GGUF and MLX weights; vision components and client integrations have their own runtime conditions.
Original release ↗