Ternary Bonsai 2 27B Uncensored Heretic swift unc needs about 9.0 GB of memory at its main file (a 6.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 6.4 GB to 7.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Ternary Bonsai 2 27B – Uncensored Heretic + Swift, 27B dense vision‑language model
Ternary Bonsai 2 27B is a 27B parameter Qwen3.8‑based model with native vision support and a 262,144‑token context. It is distributed as a single GGUF file that can be merged with a rank‑16 LoRA for Swift‑unc behaviour. The model is released under Apache‑2.0.
Good at
- Vision‑language reasoning
- Long‑horizon multi‑step tasks
- Dense inference on a single GPU
Limits
- Requires PrismML’s llama.cpp fork
- No official support in mainline llama.cpp, Ollama, LM Studio or llama.app
- Large VRAM requirement for full head quality
Best for
- Image‑to‑text generation
- Complex reasoning workflows
- Deploying on a single GPU with 8–12 GB VRAM
Who it’s for. Developers and researchers who need a compact, dense vision‑language model that can run on a single GPU. The model is suitable for applications that require long context and advanced reasoning without the overhead of a mixture‑of‑experts architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 6.4 GB | 9.0 GB | Too big | Get file → | |
| — | 7.5 GB | 10.2 GB | Too big | Get file → |
For 8 GB VRAM, use the ~6.4 GB GGUF file which requires about 9 GB of VRAM at 8 k context. For 12 GB VRAM or more, the ~7.54 GB file uses about 10.2 GB of VRAM and provides higher head quality. Both files are approximate estimates and include the full 262,144‑token context.
What GPU do you need for Ternary Bonsai 2 27B Uncensored Heretic swift unc?
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 (7.5 GB file, about 10.2 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 2 27B Uncensored Heretic swift unc
How much VRAM does Ternary Bonsai 2 27B Uncensored Heretic swift unc need?
About 9.0 GB at its main file with an 8K context window. That is the 6.4 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 Heretic swift unc on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ternary Bonsai 2 27B Uncensored Heretic swift unc GGUF?
It depends on the quant: file is 6.4 GB, file is 7.5 GB.
What context length does Ternary Bonsai 2 27B Uncensored Heretic swift unc 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 Uncensored Heretic swift unc GGUF?
The files are on Hugging Face in the hotdogs/Ternary-Bonsai-2-27B-Uncensored-Heretic-swift_unc 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 Heretic swift unc 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 ~6.4 GB GGUF file requires about 9 GB of VRAM at 8 k context, which is close to 8 GB but may need a lower context or reduced precision.
Does this model support vision?
Yes, it includes a vision projector and is a native vision‑language model.
What fork of llama.cpp is required?
It requires PrismML’s llama.cpp fork; mainline llama.cpp, Ollama, LM Studio or llama.app will not load the PQ2_0 quantization.