prism-ml/Bonsai-27B-mlx-1bit
text-generation model by prism-ml
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Prism ML Website | Whitepaper | Demo & Examples | Discord Full 27B-class reasoning in binary transformer weights — the first 27B-class model to run on a phone Each weight is a single sign bit: 0 maps to −scale, 1 maps to +scale. Every group of 128 weights shares one FP16 scale factor. Effective bits per weight: 1.125 (1 sign bit + 16-bit scale amortized over 128 weights) — an idealized 14.2x reduction vs FP16. This is the most aggressive operating point in the Bonsai 27B family: it minimizes both stored footprint and the weight traffic incurred at every decoding step, and it is what brings a 27B model within a phone's memory budget. The binary build deploys at its native 1-bit g128 layout, so ideal and deployed sizes match. The deployed figure describes the language model alone — the only component that must stay resident for text inference; a…
Read the full model card ↗ · Preview checked 2026-10-30T16:48:07.818Z
Inside the original model card — Document outline
- 1-bit Bonsai 27B
- Highlights
- Resources
- Model Overview
- Weight Representation: Binary g128
- Memory Requirement
- Shipped Components
- MLX Packaging
- Peak Memory at Context
- Best Practices
- Generation Parameters
- System Prompt
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
prism-ml/Bonsai-27B-mlx-1bit is a text-generation model repository published by prism-ml on Hugging Face. The source reports the mlx library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- mlx
- Recent downloads (30 days)
- 973,798
- Cumulative likes
- 285
- Hugging Face trending score
- 2
- Reported safetensors parameters
- 1,724,001,520
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-07-04T00:24:55.000Z
- Last modified
- 2026-07-14T21:39:12.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.6-27B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:29.042Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.