Ternary Bonsai 2 27B Steered needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.0 GB to 7.2 GB.
27B ternary transformer with 262K‑token context and refusal steering
Ternary Bonsai 2 27B Steered is a 27B‑parameter language model quantized to ternary weights. It offers 262K‑token on‑device context and a control vector that removes refusal responses. The model runs on llama.cpp, Metal, and MLX backends.
Good at
- Large context inference
- Reasoning and agentic behavior
- Refusal steering
Limits
- No vision support
- Requires at least 8.6 GB VRAM for 8K context
- License is apache‑2.0
Best for
- Chatbots needing long context
- Research on low‑bit inference
- Applications requiring refusal removal
Who it’s for. Developers and researchers building LLM applications on laptops or single GPUs. The model is suitable for environments where memory is limited but long‑form reasoning is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 7.2 GB | 8.6 GB | Too big | Get file → |
For 8 GB VRAM, use the 7.21 GB PQ2_0 pack; it needs about 8.6 GB memory at 8K context. If you have more VRAM, the smaller 0.5 GB pack can be used, but memory usage is still around 0.5 GB at 8K context.
What GPU do you need for Ternary Bonsai 2 27B Steered?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 8.6 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 2 27B Steered
How much VRAM does Ternary Bonsai 2 27B Steered need?
About 0.5 GB at its main file with an 8K context window. That is the 0.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Ternary Bonsai 2 27B Steered on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ternary Bonsai 2 27B Steered GGUF?
It depends on the quant: file is 0.0 GB, file is 7.2 GB.
Where can I download Ternary Bonsai 2 27B Steered GGUF?
The files are on Hugging Face in the Secondchancee/Ternary-Bonsai-2-27B-Steered repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Ternary Bonsai 2 27B Steered use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the 7.21 GB PQ2_0 pack requires about 8.6 GB VRAM at 8K context, which fits within an 8 GB GPU with some headroom.
Does it support vision?
No, the vision tower is shipped separately and not included in this GGUF pack.
What license does it use?
The model is released under the apache‑2.0 license.