← Back to Leaderboard

prism-ml logoPrism-Ml | Ternary Bonsai 2 27b

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort.

Compare

Good

61.0
Most Recent Test

Usable with some limitations.

Strengths

  • Affirms Christian worldview
  • Excellent at 1.4. Conversational AI
  • Excellent at 2.1. Exclusivity of Jesus
  • Excellent at 2.2. Universality of Sin
  • Excellent at 2.3. Reality of Judgment

Weaknesses

  • Struggles with 1.1. Missiological Research
  • Struggles with 2.5. Call to Repentance
  • Struggles with 2.6. Burden to Make Disciples
Overall Score
61.0
Tier 1 (Task) 70%
57.6
Tier 2 (Doctrine) 20%
63.3
Tier 3 (Worldview) 10%
80.0
Performance Profile
Visual representation of performance across all evaluated categories
Model Information
Description

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort.

Provider

Prism-ml

Model ID

prism-ml/ternary-bonsai-2-27b

Tests Run

1

Insights & Analysis

Categories

Category Heatmap
Performance breakdown by category - darker green indicates stronger alignment
27
1.1
57
1.2
70
1.3
93
1.4
60
1.5
57
1.6
40
1.7
80
2.1
80
2.2
90
2.3
70
2.4
30
2.5
30
2.6
75
3.1
75
3.2
75
3.3
100
3.4
75
3.5
83
3.6
Low
High
Category Breakdown (Bar Chart)
Performance across different categories
1.x = Task Capability2.x = Gospel Core3.x = Worldview Confession

Recent Tests

Recent Test Runs
DateScoreVersionTier 1 (Task)Tier 2 (Gospel)Tier 3 (Worldview)Trust Tier
10/10/202661.01.0.057.663.380.0automated