Ternary Bonsai 2 27B Uncensored Heretic needs about 8.6 GB of memory at its main file (a 5.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 5.9 GB to 7.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
27B‑class ternary Qwen3.8 model for low‑memory inference
Ternary Bonsai 2 27B Uncensored Heretic is a 27B‑parameter Qwen3.8 model quantized to ternary weights. It offers 262,144‑token context and retains most FP16 intelligence. The model is released under Apache‑2.0 and includes a baked Heretic LoRA.
Good at
- Reasoning and math near full precision
- Coding tasks at baseline level
- Agentic tool‑calling
Limits
- No vision support in this GGUF pack
- Reduced safety alignment
- Requires Prism‑ML llama.cpp kernels
Best for
- Research and safety testing
- Low‑memory inference on laptops
- Red‑team experimentation
Who it’s for. Researchers, safety labs, and developers needing a 27B‑class model that fits on a single GPU or a laptop. The model is intended for experimentation only and should not be deployed in public services.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 5.9 GB | 8.6 GB | Too big | Get file → | |
| — | 7.2 GB | 9.9 GB | Too big | Get file → |
For 8 GB VRAM use the PTQ1_0 pack (5.95 GB, ~8.6 GB memory at 8 k context). For 10 GB VRAM use the PQ2_0 pack (7.21 GB, ~9.9 GB memory at 8 k context). Estimates are approximate and depend on runtime kernels.
What GPU do you need for Ternary Bonsai 2 27B Uncensored Heretic?
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 (7.2 GB file, about 9.9 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 2 27B Uncensored Heretic
How much VRAM does Ternary Bonsai 2 27B Uncensored Heretic need?
About 8.6 GB at its main file with an 8K context window. That is the 5.9 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ternary Bonsai 2 27B Uncensored Heretic GGUF?
It depends on the quant: file is 5.9 GB, file is 7.2 GB.
What context length does Ternary Bonsai 2 27B Uncensored Heretic 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 GGUF?
The files are on Hugging Face in the ldov/Ternary-Bonsai-2-27B-Uncensored-Heretic-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 Heretic 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 PTQ1_0 pack is 5.95 GB and requires about 8.6 GB of VRAM at 8 k context.
Does this GGUF pack include vision support?
No, the vision tower is shipped separately and is not included in this pack.
What license does the model use?
The model is released under the Apache‑2.0 license.