TE

Ternary Bonsai 2 9B Uncensored LoRA

TernaryGGUF by AtomicChatUpdated 2026-10-28
Download on Hugging Face
Parameters9B
Context—
Layers—
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Ternary Bonsai 2 9B 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.

Ternary Bonsai 2 9B Uncensored LoRA – a 9B ternary language model with LoRA adapter

Ternary Bonsai 2 9B Uncensored LoRA is a 9B‑parameter model based on the Ternary Bonsai 2 9B backbone. It uses a rank‑1 LoRA adapter to remove a refusal direction at inference time. The model is quantized with ternary weights and runs on the PrismML llama.cpp fork.

Good at

  • Fast inference with ternary kernels
  • Low memory footprint
  • Customizable refusal control

Limits

  • Requires PrismML llama.cpp fork
  • No native vision support without mmproj
  • License is apache‑2.0

Best for

  • Local LLM deployment
  • Fine‑tuning with LoRA
  • Running on low‑VRAM GPUs

Who it’s for. Developers and researchers who need a lightweight 9B model that can be run locally with minimal VRAM. The LoRA adapter allows disabling refusal behavior without changing the base pack.

Quants & memory

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

The only available GGUF file is the ternary pack with an estimated memory usage of 0.5 GB at 8 k context. This is suitable for systems with 1 GB or more of RAM. No other quantizations are provided.

What GPU do you need for Ternary Bonsai 2 9B 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).

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters9B

Source

Quantized byAtomicChat
FamilyTernary
Licenseapache-2.0
Downloads (HF)908
Last updated2026-10-28

Frequently asked questions about Ternary Bonsai 2 9B Uncensored LoRA

How much VRAM does Ternary Bonsai 2 9B 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 9B 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 9B Uncensored LoRA GGUF?

It depends on the quant: file is 0.0 GB.

Where can I download Ternary Bonsai 2 9B Uncensored LoRA GGUF?

The files are on Hugging Face in the AtomicChat/Ternary-Bonsai-2-9B-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 9B 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 ternary pack requires only about 0.5 GB of RAM at 8 k context, well within an 8 GB VRAM budget.

Does this model support vision input?

Vision input is available through a separate mmproj pack (Q8_0). It must be loaded only when an image arrives.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Ternary-Bonsai-2-9B-gguf

Similar models

Browse all →

More from AtomicChat

All by AtomicChat →

More Ternary models

All Ternary →

Other small models

All small models →