View on models.dev Introducing Ternary Bonsai 2 2B, 4B, and 9B: Bringing Local Agents to Everyday Devices
Today, we’re expanding the Bonsai 2 family with three new ternary models based on Qwen3.5: Ternary Bonsai 2 2B, 4B, and 9B.
PrismML
Ternary Bonsai 2 27B
PrismML
A ternary 27B multimodal reasoning model based on Qwen3.8, supporting coding, mathematics, image understanding, and tool use.
Specs
Model
- Family
- Bonsai 2
- Variant
- 27B
- Parameters
- 27B
- Weights
- Open
- License
- Apache-2.0
Limits
- Context
- 262,144 tokens
- Max output
- 32,768 tokens
Modalities
- Input
- Text Image
- Output
- Text
Pricing
- Input
- $0.075 / 1M
- Output
- $0.5 / 1M
- Cache read
- $0.0375 / 1M
Capabilities
- Reasoning
- Yes
- Reasoning control
- Effort levels
- Tool calling
- Yes
- Attachments
- Yes
Dates
- Announced
- 18 Sept 2026
- Released
- 18 Sept 2026
Articles
All articlesprismml.com
More from PrismML
All modelsTernary Bonsai 2 9B
PrismML
A ternary 9B model based on Qwen3.5, built for local agents with reasoning, visual understanding, and tool use.
Apache-2.0
Ternary Bonsai 2 4B
PrismML
A ternary 4B model based on Qwen3.5, built for local agents with reasoning, visual understanding, and tool use.
Apache-2.0
Ternary Bonsai 2 2B
PrismML
A ternary 2B model based on Qwen3.5, built for local agents with reasoning, visual understanding, and tool use.
Apache-2.0