TE

Ternary Bonsai 2 27B Uncensored LoRA

TernaryGGUF by AtomicChatUpdated 2026-10-28
Download on Hugging Face
Parameters2M
Context—
Layers—
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Ternary Bonsai 2 27B Uncensored LoRA 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 3 quants, from 0.0 GB to 0.0 GB.

Ternary Bonsai 2 27B Uncensored LoRA – 27B reasoning in ternary weights

Ternary Bonsai 2 27B Uncensored LoRA is a rank‑1 LoRA adapter for the Ternary‑Bonsai‑2‑27B‑gguf base pack. It removes the refusal direction and retains full reasoning capability. The adapter is byte‑identical to the base pack and requires PrismML’s llama.cpp fork.

Good at

  • Ternary quantization for low‑memory inference
  • Uncensored reasoning without refusals
  • Compatible with llama.cpp, Metal, and MLX

Limits

  • Requires PrismML’s llama.cpp fork
  • No vision support in the adapter
  • Limited to 8k context memory estimates

Best for

  • Running on laptops with 1‑2 GB VRAM
  • Deploying on Apple Silicon with MLX
  • Testing low‑bit ternary models

Who it’s for. Developers and researchers who need a lightweight 27B model for local inference and want to remove refusal behavior. It is suitable for environments where GPU memory is constrained and custom llama.cpp kernels are available.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →

The adapter files are 0.01 GB each and estimate 0.5 GB of VRAM at 8k context. For a 1 GB VRAM budget, load the adapter with the base pack and use the PTQ1_0 or PQ2_0 kernels from the parent model. The memory usage is approximate and depends on the backend.

What GPU do you need for Ternary Bonsai 2 27B Uncensored LoRA?

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).

Which Ternary Bonsai 2 27B Uncensored LoRA quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters2M

Source

Quantized byAtomicChat
FamilyTernary
Licenseapache-2.0
Downloads (HF)1,579
Last updated2026-10-28

Frequently asked questions about Ternary Bonsai 2 27B Uncensored LoRA

How much VRAM does Ternary Bonsai 2 27B Uncensored LoRA 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 Uncensored LoRA 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 Uncensored LoRA GGUF?

It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB.

Where can I download Ternary Bonsai 2 27B Uncensored LoRA GGUF?

The files are on Hugging Face in the AtomicChat/Ternary-Bonsai-2-27B-Uncensored-LoRA-GGUF 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 Uncensored LoRA 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 adapter and base pack together use about 0.5 GB at 8k context, well below 8 GB.

Does it support vision?

No, the adapter contains only language weights; the vision tower is a separate Q8_0 mmproj pack.

Do I need a special llama.cpp build?

Yes, stock llama.cpp cannot open the base pack; use PrismML’s llama.cpp fork.

Other GGUFs of Ternary-Bonsai-2-27B-gguf

Similar models

Browse all →

More from AtomicChat

All by AtomicChat →

More Ternary models

All Ternary →

Other tiny models

All tiny models →