Bonsai 27b Ternary CRACK needs about 10.9 GB of memory at Q2_0 (a 8.2 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.
Bonsai 27b Ternary CRACK – 27B ternary transformer for on‑device reasoning
Bonsai 27b Ternary CRACK is a 27B‑class language model quantized to Q2_0. It supports 262,144‑token context and retains vision, reasoning, and tool use. The model is released under Apache‑2.0 and is compatible with llama.cpp, Metal, and MLX.
Good at
- Large context reasoning
- Vision‑language support
- Tool‑use and agentic behavior
Limits
- No high‑precision escape hatches
- Requires Prism llama.cpp fork
- No GPU‑only support for 8‑bit kernels
Best for
- On‑device inference on laptops
- Embedded vision applications
- Low‑latency text generation
Who it’s for. Developers needing a 27B‑class model that fits on a single GPU or a laptop. Ideal for applications that require large context and vision‑language capabilities without high‑precision weights.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_0 | 8.2 GB | 10.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_0 (8.25 GB file). Memory estimate is approx 10.9 GB at 8 k context. If VRAM is limited, consider the 1‑bit companion (~3.9 GB).
What GPU do you need for Bonsai 27b Ternary CRACK?
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 Q2_0 (8.2 GB file, about 10.9 GB in use).
Which Bonsai 27b Ternary CRACK quant should you choose?
Q2_0 (8.2 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Bonsai 27b Ternary CRACK
How much VRAM does Bonsai 27b Ternary CRACK need?
About 10.9 GB at Q2_0 with an 8K context window. That is the 8.2 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 Bonsai 27b Ternary CRACK on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Bonsai 27b Ternary CRACK GGUF?
It depends on the quant: Q2_0 is 8.2 GB.
What context length does Bonsai 27b Ternary CRACK 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 Bonsai 27b Ternary CRACK GGUF?
The files are on Hugging Face in the dealignai/Bonsai-27b-Ternary-CRACK-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 Bonsai 27b Ternary CRACK 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.
Does the model support vision tasks?
Yes, it includes a Qwen3VL vision tower and supports image input.
What license applies to this model?
The model is released under the Apache‑2.0 license.