Ternary Bonsai 2 27B needs about 9.9 GB of memory at its main file (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.9 GB to 53.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Ternary Bonsai 2 27B – 27B‑parameter vision‑language model in ternary GGUF format
Ternary Bonsai 2 27B is a 27‑billion‑parameter vision‑language model based on Qwen3.8‑27B. It offers 262,144‑token context and is available in two ternary GGUF packs, PTQ1_0 (5.95 GB) and PQ2_0 (7.21 GB). The model retains 98.2 % of FP16 intelligence and runs on llama.cpp, Metal, CUDA, and MLX.
Good at
- Vision‑language reasoning
- Large‑context text generation
- Agentic tool‑calling
Limits
- No native vision support in llama.cpp without separate Q8_0 pack
- Requires 8 k context for memory estimates
- License is Apache‑2.0
Best for
- On‑device inference on laptops or single GPUs
- Low‑latency vision‑language tasks
- Fine‑tuning with limited VRAM
Who it’s for. Developers needing a compact, on‑device vision‑language model for edge inference. The model is suitable for applications that require large context and reasoning capabilities without high‑precision hardware.
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 → | |
| F16 | 53.8 GB | 56.5 GB | Too big | Get file → |
For 8 GB VRAM, use the PTQ1_0 pack (5.95 GB) which needs about 8.6 GB of RAM at 8 k context. If 12 GB VRAM is available, the PQ2_0 pack (7.21 GB) can be used, requiring roughly 9.9 GB of RAM. The FP16 pack is not recommended for low‑memory devices.
What GPU do you need for Ternary Bonsai 2 27B?
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).
- 16 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 9.9 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 9.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 9.9 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 9.9 GB in use).
Which Ternary Bonsai 2 27B quant should you choose?
If memory is tight, the smallest file is the first one in the table at 5.9 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 2 27B
How much VRAM does Ternary Bonsai 2 27B need?
About 9.9 GB at its main file with an 8K context window. That is the 7.2 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 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 GGUF?
It depends on the quant: file is 5.9 GB, file is 7.2 GB, F16 is 53.8 GB.
What context length does Ternary Bonsai 2 27B 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 GGUF?
The files are on Hugging Face in the prism-ml/Ternary-Bonsai-2-27B-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 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 Ternary Bonsai 2 27B on a laptop with 8 GB VRAM?
Yes, the PTQ1_0 pack is 5.95 GB and requires about 8.6 GB of RAM at 8 k context, which fits on an 8 GB VRAM laptop.
Does the model support vision tasks in llama.cpp?
Vision support requires a separate Q8_0 mmproj pack; llama.cpp can load it but it is not bundled in the GGUF files.
What license applies to this model?
The model is released under the Apache‑2.0 license.