Bonsai 27B (1-bit and ternary) released
Prism ML · Model release
Source confirmed
Ternary Bonsai 27B
Released Jul 14, 2026 — see all recent releases
Decision reading
Ternary Bonsai 27B is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Data as of September 10, 2026 · How the score is built
Share or export
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- prism-ml/Ternary-Bonsai-27B-ggufPrismML Ternary Bonsai 27B model card
- Context window
- 262KPrismML Ternary Bonsai 27B model card
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- PrismML publishes the ternary (Q2_0_g128, 1.71 bits per weight) GGUF of its Qwen3.6-27B-derived model under Apache 2.0, a 7.2 GB deployment for llama.cpp with the full 262K context.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordPrismML Ternary Bonsai 27B model card
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersLineage
The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Jul 14, 2026 · you are here
Ternary Bonsai 27BNot publicly ranked · Price not listed
27b
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Ternary Bonsai 27B, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Ternary Bonsai 27B is a open weight model with a 262K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
PrismML publishes the ternary (Q2_0_g128, 1.71 bits per weight) GGUF of its Qwen3.6-27B-derived model under Apache 2.0, a 7.2 GB deployment for llama.cpp with the full 262K context.
PrismML’s July 14, 2026 model card reports the Ternary Bonsai 27B at 80.49 average across its thinking-mode suite (94.6% of the Qwen3.6-27B FP16 score) and publishes only per-category averages, so BenchLM stores no scored rows. The row stays unranked.
Ternary Bonsai 27B sits in the Ternary Bonsai family with Ternary Bonsai 8B, Ternary Bonsai 1.7B, Ternary Bonsai 4B. The profile has no source-displayable benchmark row yet.
Radar
Full release historyTernary Bonsai 27B release history
Radar confirmed these at the source. Use Ternary Bonsai 27B in your work? Explore Radar to follow supported changes and choose your alerts.
Frequently asked questions
How does Ternary Bonsai 27B perform overall in AI benchmarks?
Ternary Bonsai 27B does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Is Ternary Bonsai 27B open source?
Ternary Bonsai 27B is an open-weight model from Prism ML. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to Ternary Bonsai 27B?
Ternary Bonsai 27B belongs to the Ternary Bonsai family. Related tracked variants include Ternary Bonsai 8B, Ternary Bonsai 1.7B, Ternary Bonsai 4B. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Ternary Bonsai 27B have full benchmark coverage on BenchLM?
No. Ternary Bonsai 27B currently has 0 source-displayable rows across 434 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Ternary Bonsai 27B?
Ternary Bonsai 27B has a documented context window of 262K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.
Compare Ternary Bonsai 27B with every tracked model482 comparisons
Last updated September 10, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch Ternary Bonsai 27B in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.