prism ml 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.
Prism ML Ternary Bonsai 2 27B – a dense 27B model in ternary weights
Prism ML Ternary Bonsai 2 27B is a 26.9B parameter model based on Qwen3.8. It supports reasoning, tools, and vision in a compact ternary format. The model is available in three GGUF quantizations, including a 5.95 GB file and a 53.81 GB FP16 file.
Good at
- Reasoning
- Tools
- Vision
Limits
- Requires ~8.6 GB VRAM for 8k context (5.95 GB file)
- 53.81 GB FP16 file is large
- Apache‑2.0 license
Best for
- Complex reasoning tasks
- Agentic tool‑calling
- Vision‑language applications
Who it’s for. Developers and researchers who need a dense 27B model that fits on a single GPU or laptop while retaining most FP16 intelligence. The ternary quantization allows deployment on systems with limited VRAM.
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 5.95 GB quantized file; it estimates 8.6 GB VRAM at 8k context. For higher memory budgets, the 7.21 GB file uses about 9.9 GB VRAM. For maximum precision, use the 53.81 GB FP16 file, which requires ~56.5 GB VRAM at 8k context.
What GPU do you need for prism ml 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 prism ml 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 prism ml Ternary Bonsai 2 27B
How much VRAM does prism ml 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 prism ml 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 prism ml 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 prism ml 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 prism ml Ternary Bonsai 2 27B GGUF?
The files are on Hugging Face in the nesoai-dev/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 prism ml 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 this model on 8 GB VRAM?
Yes, the 5.95 GB quantized file uses about 8.6 GB VRAM at 8k context, which fits on an 8 GB GPU with some headroom.
Does this model support vision?
Yes, the model includes vision capability as part of its detected abilities.
What license does it use?
The model is released under the Apache‑2.0 license.