jev Ternary Bonsai 2 27B Abliterated PTQ1 0 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. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
JEV Ternary Bonsai 2 27B Abliterated + JEV Decision LoRA (PTQ1_0 GGUF)
JEV Ternary Bonsai 2 27B is a 27‑billion parameter Qwen3.5‑based model. It is abliterated to reduce refusal and includes a JEV Decision LoRA for structured decision outputs. The model is distributed as a PrismML ternary GGUF pack.
Good at
- Reduced refusal behaviour
- Structured decision output
- Low‑bit ternary format
Limits
- Requires PrismML llama.cpp fork
- No vision support
- 8.6 GB memory at 8 k context
Best for
- Chat with decision prompts
- Short direct answers
- Non‑thinking mode usage
Who it’s for. Developers needing a lightweight 27B model with minimal refusal and decision‑oriented responses. Suitable for local deployment on systems with sufficient VRAM and the PrismML llama.cpp fork.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 5.9 GB | 8.6 GB | Too big | Get file → |
The only available quant is PTQ1_0 ternary. File size is 5.9 GB and requires approximately 8.6 GB of VRAM at 8 k context. Use this quant if your GPU meets that memory budget.
What GPU do you need for jev Ternary Bonsai 2 27B Abliterated PTQ1 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 (5.9 GB file, about 8.6 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about jev Ternary Bonsai 2 27B Abliterated PTQ1 0
How much VRAM does jev Ternary Bonsai 2 27B Abliterated PTQ1 0 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 jev Ternary Bonsai 2 27B Abliterated PTQ1 0 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 jev Ternary Bonsai 2 27B Abliterated PTQ1 0 GGUF?
It depends on the quant: file is 5.9 GB.
What context length does jev Ternary Bonsai 2 27B Abliterated PTQ1 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 jev Ternary Bonsai 2 27B Abliterated PTQ1 0 GGUF?
The files are on Hugging Face in the hotdogs/jev-Ternary-Bonsai-2-27B-Abliterated-PTQ1_0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does jev Ternary Bonsai 2 27B Abliterated PTQ1 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 about 8.6 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision?
No. The model has no vision capability.
What fork of llama.cpp is required?
It requires the PrismML llama.cpp fork to load the PTQ1_0 ternary pack.