Bonsai 27B (1-bit and ternary) released
Prism ML · Model release
Source confirmed
Data as of September 30, 2026 · How the score is built
CurrentOpen WeightReasoning
Released Jul 14, 2026262K contextPrismML 1-bit Bonsai 27B model card
1-bit Bonsai 27B
Decision reading1-bit 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.
Released Jul 14, 2026 — see all recent releases
1-bit Bonsai 27B will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Radar
Full release history1-bit Bonsai 27B release history
Radar confirmed these at the source. Use 1-bit Bonsai 27B in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
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/Bonsai-27B-ggufPrismML 1-bit Bonsai 27B model card
- Context window
- 262KPrismML 1-bit 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 1-bit (Q1_0_g128) GGUF of its Qwen3.6-27B-derived model under Apache 2.0, a 3.9 GB deployment that runs full 262K context on llama.cpp (CUDA, Metal, CPU) and on an iPhone 17 Pro.
- 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 1-bit Bonsai 27B model card
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
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 1-bit 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.
1-bit 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 1-bit (Q1_0_g128) GGUF of its Qwen3.6-27B-derived model under Apache 2.0, a 3.9 GB deployment that runs full 262K context on llama.cpp (CUDA, Metal, CPU) and on an iPhone 17 Pro.
PrismML’s July 14, 2026 model card reports the 1-bit Bonsai 27B at 76.11 average across its thinking-mode suite (89.5% of the Qwen3.6-27B FP16 score of 85.07) and publishes only per-category averages, so no individual benchmark has an exact lane and BenchLM stores no scored rows. The row stays unranked.
1-bit Bonsai 27B sits in the Bonsai family with 1-bit Bonsai 8B, 1-bit Bonsai 1.7B, 1-bit Bonsai 4B. The profile has no source-displayable benchmark row yet.
Last updated September 30, 2026. Runtime fields remain blank until a sourced snapshot exists.
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 parametersQuestions
How does 1-bit Bonsai 27B perform overall in AI benchmarks?
1-bit 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 1-bit Bonsai 27B open source?
1-bit 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 1-bit Bonsai 27B?
1-bit Bonsai 27B belongs to the Bonsai family. Related tracked variants include 1-bit Bonsai 8B, 1-bit Bonsai 1.7B, 1-bit 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 1-bit Bonsai 27B have full benchmark coverage on BenchLM?
No. 1-bit Bonsai 27B currently has 0 source-displayable rows across 495 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 1-bit Bonsai 27B?
1-bit 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.