Identity
- Status
- active
- Developer ID
prism-ml/Bonsai-27B- Released
- Jul 4, 2026
- Version
- Bonsai 27B
- License
- apache-2.0
PrismMLBonsai 27B
PrismML's 1-bit multimodal Qwen3.6 27B derivative with local vision, reasoning, and tool-calling support.
- Token context
- 262K tokens
- Inputs
- Text, Image
- Outputs
- Text
- Released
- Jul 4, 2026
Providers & Pricing
0 current sourced offerings
No Hosted API AvailableThis record is downloadable or self-hosted. Its cost depends on the infrastructure and serving configuration, not a universal model price.
At a Glance
Model Facts
Capacity
- Token context
- 262K tokens
- Maximum output
- Unknown
- Total parameters
- 27B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image
- Outputs
- Text
- API available
- No
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- Yes
- Tool calling
- Yes
- Capabilities
- chat, generation, reasoning, tools, vision
Technical Specifications
- Base model
- Qwen3.6 27B
- Weight format
- Binary Q1_0
- Effective bit width
- 1 bit per weight
- Language model size
- 3.53 GiB
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/Bonsai-27B, prism-ml/Bonsai-27B-gguf, prism-ml/Bonsai-27B-mlx-1bit
Explicit Unknowns
- Maximum output
- Architecture
- Tokenizer
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Bonsai 27BPrismML | vs |  GPT-6 AstraOpenAI | cross-developer peersimage, text |
Bonsai 27BPrismML | vs | Claude Fable 5.1Anthropic | cross-developer peersimage, text |
Bonsai 27BPrismML | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
Bonsai 27BPrismML | vs |  DeepSeek V4.1 FlashDeepSeek | cross-developer peersimage, text |
Bonsai 27BPrismML | vs | Grok 4.6xAI | cross-developer peersimage, text |
Bonsai 27BPrismML | vs |  Qwen3.8 MaxQwen | cross-developer peersimage, text |
Bonsai 27BPrismML | vs |  Kimi K3Moonshot AI | cross-developer peersimage, text |
Bonsai 27BPrismML | vs |  MiniMax M3MiniMax | cross-developer peersimage, text |
Bonsai 27BPrismML | vs |  GLM 5.3Z.ai | cross-developer peerstext |
Bonsai 27BPrismML | vs |  Hy4 previewTencent | cross-developer peerstext |
Bonsai 27BPrismML | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage, text |
Bonsai 27BPrismML | vs |  Mistral Large 3Mistral AI | cross-developer peersimage, text |
Bonsai 27BPrismML | vs | cross-developer peersimage, text | |
Bonsai 27BPrismML | vs |  Nova 2 LiteAmazon | cross-developer peersimage, text |
Bonsai 27BPrismML | vs | cross-developer peersimage, text | |
Bonsai 27BPrismML | vs |  ERNIE 5.1Baidu | cross-developer peerstext |
Bonsai 27BPrismML | vs | cross-developer peerstext | |
Bonsai 27BPrismML | vs | cross-developer peerstext | |
Bonsai 27BPrismML | vs |  Phi-4 ReasoningMicrosoft | cross-developer peerstext |
Bonsai 27BPrismML | vs | cross-developer peerstext | |
Bonsai 27BPrismML | vs |  Sonar ProPerplexity | cross-developer peerstext |
Bonsai 27BPrismML | vs | Claude Mythos 5.1Anthropic | cross-developer peersimage, text |
Questions
Bonsai 27B FAQs
What is Bonsai 27B?+
PrismML's 1-bit multimodal Qwen3.6 27B derivative with local vision, reasoning, and tool-calling support. It is developed by PrismML and its current sourced lifecycle status is active.
What inputs and outputs does Bonsai 27B support?+
Bonsai 27B's current record lists Text and Image as input and Text as output.
How much context does Bonsai 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 Bonsai 27B?+
Bonsai 27B's developer-published specifications include base model: Qwen3.6 27B; weight format: Binary Q1_0; effective bit width: 1 bit per weight; language model size: 3.53 GiB.
How large is Bonsai 27B?+
The current record lists 27B total parameters and an unknown active parameter count. Its architecture is not reported.
What capabilities and tasks does Bonsai 27B support?+
Bonsai 27B's recorded capabilities are chat, generation, reasoning, tools, and vision. Its supported tasks are image, reasoning, and text.
Is Bonsai 27B available through an API?+
Bonsai 27B is explicitly marked as not API-available in the current record.
How much does Bonsai 27B cost through an API?+
Bonsai 27B has no verified hosted API offering, so no provider token price applies. It is a downloadable or self-hosted artifact whose cost depends on the serving infrastructure and workload.
Can Bonsai 27B be self-hosted?+
Bonsai 27B is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Bonsai 27B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are prism-ml/Bonsai-27B, prism-ml/Bonsai-27B-gguf, and prism-ml/Bonsai-27B-mlx-1bit.