Ternary Bonsai 2 27B 262k needs about 9.1 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. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Ternary Bonsai 2 27B 262k – 27B reasoning in ternary weights for llama.cpp
Ternary Bonsai 2 27B 262k delivers full 27B‑class reasoning with a 262,144‑token context window. The model uses ternary weights and a hybrid‑attention backbone, enabling efficient inference on a single GPU or laptop. It retains 98.2 % of FP16 intelligence and supports tool usage.
Good at
- Large context inference
- Ternary weight efficiency
- Tool‑aware reasoning
Limits
- No vision support
- Requires 5.9 GB GGUF file
- No high‑precision escape hatches
Best for
- On‑device reasoning with long context
- Agentic tool‑calling tasks
- Low‑latency inference on single GPU
Who it’s for. Developers needing a 27B‑class model that fits on a single GPU or laptop. The model is suitable for applications that require long‑context reasoning and tool usage without vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 6.4 GB | 9.1 GB | Too big | Get file → |
The only available GGUF pack is PTQ1_0 with a 6.4 GB file. It requires approximately 9.1 GB of VRAM at 8 k context. For lower VRAM budgets, no alternative quant is provided in the file list, so the model cannot be run with a smaller quant.
What GPU do you need for Ternary Bonsai 2 27B 262k?
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 (6.4 GB file, about 9.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 2 27B 262k
How much VRAM does Ternary Bonsai 2 27B 262k need?
About 9.1 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 262k on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ternary Bonsai 2 27B 262k GGUF?
It depends on the quant: file is 6.4 GB.
What context length does Ternary Bonsai 2 27B 262k support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Ternary Bonsai 2 27B 262k GGUF?
The files are on Hugging Face in the CaryPalmer/Ternary-Bonsai-2-27B-262k-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 262k 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?
The PTQ1_0 pack needs about 9.1 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision tasks?
No, the model contains only language weights; the vision tower is separate.
What license applies to this model?
The model is released under the Apache 2.0 license.