Identity
- Status
- active
- Developer ID
prism-ml/Bonsai-Image-Ternary-4B- Released
- May 21, 2026
- Version
- Bonsai Image Ternary 4B
- License
- apache-2.0
PrismMLBonsai Image Ternary 4B
PrismML's compact ternary FLUX.2 Klein 4B derivative for local text-to-image generation.
- Token context
- Unknown
- Inputs
- Text
- Outputs
- Image
- Released
- May 21, 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
- Unknown
- Maximum output
- Unknown
- Total parameters
- 4B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Image
- API available
- No
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- Yes
- Tool calling
- No
- Capabilities
- generation
Technical Specifications
- Base model
- FLUX.2 Klein 4B
- Weight format
- Ternary weights with FP16 group scales
- Transformer size
- 1.21 GB
- Default resolution
- 512 × 512
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-Image-Ternary-4B, prism-ml/bonsai-image-ternary-4B-gemlite-2bit, prism-ml/bonsai-image-ternary-4B-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 |
|---|---|---|---|
Bonsai Image Ternary 4BPrismML | vs |  GPT-6 AstraOpenAI | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs | Claude Fable 5.1Anthropic | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peers |
Bonsai Image Ternary 4BPrismML | vs |  DeepSeek V4.1 FlashDeepSeek | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs | Grok 4.6xAI | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs |  Qwen3.8 MaxQwen | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs |  Kimi K3Moonshot AI | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs |  MiniMax M3MiniMax | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs |  GLM 5.3Z.ai | cross-developer peers |
Bonsai Image Ternary 4BPrismML | vs |  Hy4 previewTencent | cross-developer peers |
Bonsai Image Ternary 4BPrismML | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs |  Mistral Large 3Mistral AI | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs | cross-developer peersimage | |
Bonsai Image Ternary 4BPrismML | vs |  Nova 2 LiteAmazon | cross-developer peersimage |
Bonsai Image Ternary 4BPrismML | vs | cross-developer peersimage | |
Bonsai Image Ternary 4BPrismML | vs |  ERNIE 5.1Baidu | cross-developer peers |
Bonsai Image Ternary 4BPrismML | vs | cross-developer peers | |
Bonsai Image Ternary 4BPrismML | vs | cross-developer peers | |
Bonsai Image Ternary 4BPrismML | vs |  Phi-4 ReasoningMicrosoft | cross-developer peers |
Bonsai Image Ternary 4BPrismML | vs | cross-developer peers | |
Bonsai Image Ternary 4BPrismML | vs |  Sonar ProPerplexity | cross-developer peers |
Bonsai Image Ternary 4BPrismML | vs | Claude Mythos 5.1Anthropic | cross-developer peersimage |
Questions
Bonsai Image Ternary 4B FAQs
What is Bonsai Image Ternary 4B?+
PrismML's compact ternary FLUX.2 Klein 4B derivative for local text-to-image generation. It is developed by PrismML and its current sourced lifecycle status is active.
What inputs and outputs does Bonsai Image Ternary 4B support?+
Bonsai Image Ternary 4B's current record lists Text as input and Image as output.
What technical specifications are published for Bonsai Image Ternary 4B?+
Bonsai Image Ternary 4B's developer-published specifications include base model: FLUX.2 Klein 4B; weight format: Ternary weights with FP16 group scales; transformer size: 1.21 GB; default resolution: 512 × 512.
Is Bonsai Image Ternary 4B available through an API?+
Bonsai Image Ternary 4B is explicitly marked as not API-available in the current record.
How large is Bonsai Image Ternary 4B?+
The current record lists 4B total parameters and an unknown active parameter count. Its architecture is not reported.
What capabilities and tasks does Bonsai Image Ternary 4B support?+
Bonsai Image Ternary 4B's recorded capabilities are generation. Its supported tasks are image-generation.
How much does Bonsai Image Ternary 4B cost through an API?+
Bonsai Image Ternary 4B 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 Image Ternary 4B be self-hosted?+
Bonsai Image Ternary 4B is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Bonsai Image Ternary 4B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are prism-ml/Bonsai-Image-Ternary-4B, prism-ml/bonsai-image-ternary-4B-gemlite-2bit, and prism-ml/bonsai-image-ternary-4B-mlx-2bit.
Which models can Bonsai Image Ternary 4B be compared with?+
The current compatible peer set includes GPT-6 Astra, Claude Fable 5.1, Gemini 3.1 Pro, DeepSeek V4.1 Flash, and Grok 4.6. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →