Bonsai Image 4B

Released
2026-05-26
Last refreshed
2026-10-22
Status
Researched today
Open sourceCommercial use: permittedMultimodal

Bonsai Image 4B is available now for general LLM work with open-source; evaluate it while provider pricing coverage matures.

PrismML releases · 14 in the last 12 monthsChangelog →
Specifications
Family
Bonsai
Released
2026-05-26
Parameters
4B
Architecture
Diffusion Transformer
Specialization
image-generation
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Created by
PrismML

PrismML (Prism ML, Inc.) builds ultra-dense 1-bit and ternary Bonsai models for on-device and efficient datacenter infer

Website
Pricing

No tracked provider pricing is available yet.

Links
Website HuggingFace

About

Bonsai Image 4B is PrismML's 1-bit text-to-image model, built from FLUX.2 Klein 4B by moving the diffusion transformer to binary weights. The transformer is 0.93 GB (8.3x smaller than FP16) and the full Apple Silicon payload is 3.42 GB, so it runs on iPhone, Mac and CUDA GPUs. PrismML reports 88% of FLUX.2 Klein 4B's quality across GenEval, HPSv3 and DPG-Bench. Apache 2.0.

Providers

No active provider routes are tracked for this model yet.

Capabilities

VisionMultimodal

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

1-bit Bonsai Image 4Bbonsai-image-binary-4B-mlx-1bitbonsai-image-binary-4B-gemlite-1bitbonsai-image-binary-4B-unpacked