Ternary Bonsai 2 27B ABLITERATED UNCENSORED PHILADELPHIA CLASS needs about 7.2 GB of memory at its main file (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 0.0 GB to 12.4 GB (Q8_0).
Ternary Bonsai 2 27B ABLITERATED UNCENSORED PHILADELPHIA CLASS – 27B ternary transformer on disk
Ternary Bonsai 2 27B is a 26.9B parameter model using ternary weights. It retains 98.2% of FP16 intelligence and supports 262K‑token context. The model is available in multiple GGUF packings for llama.cpp and MLX.
Good at
- High‑precision reasoning with low‑bit ternary weights
- Large context on‑device inference
- Efficient on Apple MLX and CUDA
Limits
- No vision support in GGUF packings
- Requires 8k context for memory estimates
- License is apache‑2.0
Best for
- On‑device reasoning tasks
- Low‑memory inference on laptops
- Hybrid‑attention workloads
Who it’s for. Developers needing a compact 27B model with ternary weights for on‑device inference. The model is suitable for research and production environments that can run llama.cpp or MLX backends.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 5.9 GB | 7.2 GB | Fits | Get file → | |
| Q4_0 | 8.6 GB | 10.1 GB | Too big | Get file → | |
| Q8_0 | 12.4 GB | 14.3 GB | Too big | Get file → |
For 8 GB VRAM, use the 5.95 GB PTQ1_0 packing (est. 7.2 GB at 8k context). For 12 GB VRAM, the 8.56 GB Q4_0 packing (est. 10.1 GB) is suitable. The 12.36 GB Q8_0 packing (est. 14.3 GB) requires larger memory budgets.
What GPU do you need for Ternary Bonsai 2 27B ABLITERATED UNCENSORED PHILADELPHIA CLASS?
These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (5.9 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (8.6 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.4 GB file, about 14.3 GB in use).
Which Ternary Bonsai 2 27B ABLITERATED UNCENSORED PHILADELPHIA CLASS quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.0 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 ABLITERATED UNCENSORED PHILADELPHIA CLASS
How much VRAM does Ternary Bonsai 2 27B ABLITERATED UNCENSORED PHILADELPHIA CLASS need?
About 7.2 GB at its main file with an 8K context window. That is the 5.9 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 ABLITERATED UNCENSORED PHILADELPHIA CLASS on an 8 GB GPU?
Yes, with the smaller files: the 5.9 GB file needs about 7.2 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 ABLITERATED UNCENSORED PHILADELPHIA CLASS GGUF?
It depends on the quant: file is 0.0 GB, file is 5.9 GB, Q4_0 is 8.6 GB, Q8_0 is 12.4 GB.
Where can I download Ternary Bonsai 2 27B ABLITERATED UNCENSORED PHILADELPHIA CLASS GGUF?
The files are on Hugging Face in the PhillyLabs/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-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 ABLITERATED UNCENSORED PHILADELPHIA CLASS 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 8 GB VRAM?
Yes, the 5.95 GB PTQ1_0 GGUF file uses about 7.2 GB at 8k context, fitting within 8 GB VRAM.
Does the model support vision tasks?
The GGUF packings do not include vision; the vision tower is bundled only in the original MLX release.
What license applies to this model?
The model is released under the apache‑2.0 license.