Identity
- Status
- active
- Developer ID
prism-ml/Ternary-Bonsai-2-27B- Released
- Sep 17, 2026
- Version
- Ternary Bonsai 2 27B
- License
- apache-2.0
PrismMLTernary Bonsai 2 27B
PrismML's ternary multimodal Qwen3.8 27B derivative with a 262,144-token context and a 5.93 GB language-model artifact.
- Token context
- 262K tokens
- Inputs
- Text, Image
- Outputs
- Text
- Released
- Sep 17, 2026
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 OpenrouterAvailable | $0.075 | $0.50 | — | — | Sep 22, 2026 | Provider-reported |
At a Glance
Model Facts
Capacity
- Token context
- 262K tokens
- Maximum output
- Unknown
- Total parameters
- 27.4B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- Yes
- Tool calling
- Yes
- Capabilities
- chat, generation, reasoning, tools, vision
Technical Specifications
- Base model
- Qwen3.8 27B
- Weight format
- Ternary g128 with FP16 group scales
- Effective bit width
- 1.76 bits per weight
- Language model size
- 5.93 GB
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesprism-ml/Ternary-Bonsai-2-27B, prism-ml/Ternary-Bonsai-2-27B-gguf, prism-ml/Ternary-Bonsai-2-27B-mlx-2bit
Explicit Unknowns
- Maximum output
- Architecture
- Tokenizer
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Ternary Bonsai 2 27BPrismML | vs |  GPT-6 AstraOpenAI | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs | Claude Fable 5.1Anthropic | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
Ternary Bonsai 2 27BPrismML | vs |  DeepSeek V4.1 FlashDeepSeek | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs | Grok 4.6xAI | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs |  Qwen3.8 MaxQwen | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs |  Kimi K3Moonshot AI | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs |  MiniMax M3MiniMax | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs |  GLM 5.3Z.ai | cross-developer peerstext |
Ternary Bonsai 2 27BPrismML | vs |  Hy4 previewTencent | cross-developer peerstext |
Ternary Bonsai 2 27BPrismML | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs |  Mistral Large 3Mistral AI | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs | cross-developer peersimage, text | |
Ternary Bonsai 2 27BPrismML | vs |  Nova 2 LiteAmazon | cross-developer peersimage, text |
Ternary Bonsai 2 27BPrismML | vs | cross-developer peersimage, text | |
Ternary Bonsai 2 27BPrismML | vs |  ERNIE 5.1Baidu | cross-developer peerstext |
Ternary Bonsai 2 27BPrismML | vs | cross-developer peerstext | |
Ternary Bonsai 2 27BPrismML | vs | cross-developer peerstext | |
Ternary Bonsai 2 27BPrismML | vs |  Phi-4 ReasoningMicrosoft | cross-developer peerstext |
Ternary Bonsai 2 27BPrismML | vs | cross-developer peerstext | |
Ternary Bonsai 2 27BPrismML | vs |  Sonar ProPerplexity | cross-developer peerstext |
Ternary Bonsai 2 27BPrismML | vs | Claude Mythos 5.1Anthropic | cross-developer peersimage, text |
Questions
Ternary Bonsai 2 27B FAQs
What is Ternary Bonsai 2 27B?+
PrismML's ternary multimodal Qwen3.8 27B derivative with a 262,144-token context and a 5.93 GB language-model artifact. It is developed by PrismML and its current sourced lifecycle status is active.
What inputs and outputs does Ternary Bonsai 2 27B support?+
Ternary Bonsai 2 27B's current record lists Text and Image as input and Text as output.
How much context does Ternary Bonsai 2 27B support?+
The current record lists a 262K-token context window and does not report a maximum output length.
What technical specifications are published for Ternary Bonsai 2 27B?+
Ternary Bonsai 2 27B's developer-published specifications include base model: Qwen3.8 27B; weight format: Ternary g128 with FP16 group scales; effective bit width: 1.76 bits per weight; language model size: 5.93 GB.
How large is Ternary Bonsai 2 27B?+
The current record lists 27.4B total parameters and an unknown active parameter count. Its architecture is not reported.
What capabilities and tasks does Ternary Bonsai 2 27B support?+
Ternary Bonsai 2 27B's recorded capabilities are chat, generation, reasoning, tools, and vision. Its supported tasks are image, reasoning, and text.
Is Ternary Bonsai 2 27B available through an API?+
Ternary Bonsai 2 27B is marked as API-available. The directly sourced provider records currently include Openrouter.
How much does Ternary Bonsai 2 27B cost through an API?+
The lowest directly sourced prices currently attached to Ternary Bonsai 2 27B are $0.075 per million input tokens through Openrouter and $0.50 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
Can Ternary Bonsai 2 27B be self-hosted?+
Ternary Bonsai 2 27B is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Ternary Bonsai 2 27B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are prism-ml/Ternary-Bonsai-2-27B, prism-ml/Ternary-Bonsai-2-27B-gguf, and prism-ml/Ternary-Bonsai-2-27B-mlx-2bit.