Ternary Bonsai 2 27B DFlash2 needs about 2.7 GB of memory at Q8_0 (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
Ternary Bonsai 2 27B DFlash2 – 1.9B ternary transformer for on‑device reasoning
Ternary Bonsai 2 27B DFlash2 is a 1.9 B parameter model quantized to Q8_0. It offers 262 K‑token context and retains 98.2 % of FP16 intelligence. The model is available under an Apache‑2.0 license and runs on llama.cpp with CUDA, Metal or CPU backends.
Good at
- High‑quality reasoning and math
- Agentic tool calling
- Large context handling
Limits
- Requires ~2.7 GB VRAM at 8 k context
- No vision support – vision tower separate
- Large context may need more RAM for preprocessing
Best for
- Complex reasoning tasks
- Math problem solving
- Agentic tool‑based workflows
Who it’s for. Developers and researchers who need 27 B‑class reasoning on a single GPU or laptop. The model is ideal for applications requiring deep context and high inference quality without large FP16 models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 2.1 GB | 2.7 GB | Fits | Get file → |
The only available quant is Q8_0, 2.06 GB file size. It needs about 2.7 GB VRAM at 8 k context. For tighter budgets, no alternative quant is provided.
What GPU do you need for Ternary Bonsai 2 27B DFlash2?
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: the best quant that fits is Q8_0 (2.1 GB file, about 2.7 GB in use).
Which Ternary Bonsai 2 27B DFlash2 quant should you choose?
Q8_0 (2.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 2 27B DFlash2
How much VRAM does Ternary Bonsai 2 27B DFlash2 need?
About 2.7 GB at Q8_0 with an 8K context window. That is the 2.1 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 DFlash2 on an 8 GB GPU?
Yes, with Q8_0: the 2.1 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ternary Bonsai 2 27B DFlash2 GGUF?
It depends on the quant: Q8_0 is 2.1 GB.
What context length does Ternary Bonsai 2 27B DFlash2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.7 GB at 32K.
Where can I download Ternary Bonsai 2 27B DFlash2 GGUF?
The files are on Hugging Face in the ProCreations/Ternary-Bonsai-2-27B-DFlash2 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 DFlash2 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 an 8 GB VRAM GPU?
Yes, the Q8_0 quant requires approximately 2.7 GB VRAM at 8 k context, well below 8 GB.
Does this model support vision tasks?
No, the vision tower is a separate Q8_0 mmproj pack and is not included in this model.
What license applies to this model?
The model is released under the Apache‑2.0 license.