Bonsai Image

Bonsai Image

PrismML
Mercury 2

Mercury 2

Inception
+
+

Related Products

  • Google AI Studio
    30 Ratings
    Visit Website
  • Adobe Firefly
    25,029 Ratings
    Visit Website
  • Planview ProjectAdvantage
    121 Ratings
    Visit Website
  • MobiPDF (formerly PDF Extra)
    7,001 Ratings
    Visit Website
  • dbt
    263 Ratings
    Visit Website
  • AI Video Cut
    1 Rating
    Visit Website
  • LTX
    182 Ratings
    Visit Website
  • SmartDraw
    559 Ratings
    Visit Website
  • Asym Capital
    1 Rating
    Visit Website
  • Valant Behavioral Health EHR
    354 Ratings
    Visit Website

About

Bonsai Image Ternary 4B MLX 2-bit is a ternary-weight text-to-image diffusion transformer deployment for Apple Silicon. It is built as a quality-oriented Bonsai Image variant, using ternary {−1, 0, +1} transformer weights with FP16 group-wise scaling in the matrix-heavy transformer layers, including Q/K/V projections, output projections, and MLP weights. The model reduces the FLUX.2 Klein 4B transformer from 7.75 GB FP16 to a 1.21 GB Bonsai Image transformer, a 6.4× smaller footprint, while keeping visual quality and prompt fidelity close to the original model. The Apple Silicon deployment payload is 3.88 GB, including the MLX 2-bit diffusion transformer, a 4-bit Qwen3-4B text encoder, and an FP16 Flux2 VAE. After prompt encoding, the text encoder is offloaded, so the denoising loop only keeps the compact transformer and VAE resident. The model uses a 4-step FlowMatchEuler sampler with guidance 1.0 and shift 3.0, with no CFG and no negative prompts required.

About

Mercury 2 is the first reasoning model fast enough to pick up the phone, a reasoning diffusion language model built for real-time voice agents. Instead of making callers wait through seconds of dead air while an autoregressive model generates thinking tokens one by one, Mercury 2 uses a diffusion large language model architecture to generate tokens in parallel, decoding 1000+ tokens per second on standard NVIDIA GPUs. That speed is fast enough to run a full reasoning pass and start speaking within the latency budget of a natural conversation, reducing the cost of reasoning from seconds of silence to roughly 300 milliseconds. Mercury models work by corrupting clean text into noise, then training a standard Transformer to reverse the process and predict clean text across all positions simultaneously. Because each denoising pass touches many tokens, generation uses the GPU more efficiently than one-token-at-a-time decoding, making custom-silicon-like speed possible on NVIDIA H100s.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Apple Silicon developers building private local image-generation apps that need compact diffusion models

Audience

Voice AI infrastructure teams that need low-latency reasoning models for phone agents, tool-calling workflows, and natural customer conversations

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

No information available.
Free Version
Free Trial

Pricing

No information available.
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

PrismML
Founded: 2026
United States
prismml.com

Company Information

Inception
United States
www.inceptionlabs.ai/blog/mercury-2-the-first-reasoning-model-fast-enough-to-pick-up-the-phone

Alternatives

Bonsai 27B

Bonsai 27B

PrismML

Alternatives

Mercury Coder

Mercury Coder

Inception Labs
FLUX.2 [klein]

FLUX.2 [klein]

Black Forest Labs
Mercury Edit 2

Mercury Edit 2

Inception
FLUX.1

FLUX.1

Black Forest Labs
ByteDance Seed

ByteDance Seed

ByteDance
Qwen-Image

Qwen-Image

Alibaba
Uni-1

Uni-1

Luma AI

Categories

Categories

Integrations

Cerebras
GPT-4.1
Groq
Inception Labs
LiveKit
OpenAI
Pipecat
Retell AI
Vapi AI

Integrations

Cerebras
GPT-4.1
Groq
Inception Labs
LiveKit
OpenAI
Pipecat
Retell AI
Vapi AI
Claim Bonsai Image and update features and information
Claim Bonsai Image and update features and information
Claim Mercury 2 and update features and information
Claim Mercury 2 and update features and information