Skip to content

Prism Ml · Chat

Ternary Bonsai 2 27B

Prism MlChatTernary Bonsai familyOne of its sources says the weights aren't publicly available.
From Aiml API's listing:
Ternary Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3-27B. It supports coding, mathematics, tool calling and image understanding over a 262K-token context, with ternary compression shrinking the served weights. Reasoning is on by default and its effort is configurable.
Market median price
$0.1813 blended / 1M
Max context
262K
Listings
10
Providers
8

Evidence and sources

All rankings: #328 on NanoGPT recently #426 on OpenRouter today #458 on OpenRouter this week #494 on OpenRouter this monthSources: Darkbloom data docs, Models.dev data, AI/ML API data, llminfo researchPrimary data from Darkbloom from Models.dev: name, family, variant, weights availability from AI/ML API: primary mode, description from llminfo research: release date

Advantages and trade-offs

Compared with 10 representative chat models

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 Kiloprism-ml/ternary-bonsai-2-27bSources: Kilo AI Gateway data, Models.dev data262K$0.075cache read $0.0375$0.50——
 NanoGPTprism-ml/ternary-bonsai-2-27bSources: Models.dev data, NanoGPT262K$0.075cache read $0.0375$0.50——
 NanoGPTInference by DarkbloomRegions: GLBprism-ml/ternary-bonsai-2-27b · int4Source: NanoGPTNot published by the provider$0.0788cache read $0.0394$0.52539.215,155ms
 Nous Portalprism-ml/ternary-bonsai-2-27bSource: Nous Portal Inference Gateway data262K$0.075cache read $0.0375$0.50——
 OpenRouterInference by Darkbloomprism-ml/ternary-bonsai-2-27b · int4Source: OpenRouter data docs262K$0.075cache read $0.0375$0.50291,788ms
 OpenRouterprism-ml/ternary-bonsai-2-27bSources: Models.dev data, OpenRouter data docs262K$0.075cache read $0.0375$0.50——
 Darkbloomternary-bonsai-2-27b · int4Source: Darkbloom data docsNot published by the provider$0.075cache read $0.0375$0.50——

3 listings without a price are hidden.

Benchmarks

No benchmark scores yet.

Also known as: prism-ml/ternary-bonsai-2-27b

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works