Ternary Bonsai 2 27B Abliterated PQ2 0 needs about 10.9 GB of memory at its main file (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Ternary Bonsai 2 27B Abliterated PQ2_0 – 27B Qwen3.5 architecture
Ternary Bonsai 2 27B Abliterated PQ2_0 is a 27B parameter model quantised to PQ2_0. It uses a 262144 token context and is released under the Apache‑2.0 license. The model is a direct repack of the PTQ1_0 weights with a 98‑tensor ablation.
Good at
- Refusal‑ablated safety
- Maintains original capability
- Fast decode on CDNA2
Limits
- Requires PrismML llama.cpp fork
- No vision support
- Memory estimate ~10.9 GB at 8 k context
Best for
- Safety‑focused chat
- Low‑refusal content generation
- Compatibility with AMD GPUs
Who it’s for. Developers needing a safety‑ablated 27B model that runs on AMD hardware. The model is suitable for applications where the original PTQ1_0 weights are required but with a 2‑bit PQ2_0 quantisation for better performance on non‑Ampere GPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 8.2 GB | 10.9 GB | Too big | Get file → |
The single GGUF file is 8.25 GB and requires about 10.9 GB of VRAM at 8 k context. For 8 GB VRAM it will not fit; a larger VRAM budget of at least 12 GB is recommended. Use the provided file directly with the PrismML llama.cpp fork.
What GPU do you need for Ternary Bonsai 2 27B Abliterated PQ2 0?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is the main file (8.2 GB file, about 10.9 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about Ternary Bonsai 2 27B Abliterated PQ2 0
How much VRAM does Ternary Bonsai 2 27B Abliterated PQ2 0 need?
About 10.9 GB at its main file with an 8K context window. That is the 8.2 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 Abliterated PQ2 0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ternary Bonsai 2 27B Abliterated PQ2 0 GGUF?
It depends on the quant: file is 8.2 GB.
What context length does Ternary Bonsai 2 27B Abliterated PQ2 0 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Ternary Bonsai 2 27B Abliterated PQ2 0 GGUF?
The files are on Hugging Face in the davetha/Ternary-Bonsai-2-27B-Abliterated-PQ2_0-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 Abliterated PQ2 0 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?
No. The model needs approximately 10.9 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision?
No. The model has no vision capabilities.
Which llama.cpp fork is required?
The PrismML llama.cpp fork (branch prism) is required to load PQ2_0 weights.