Ternary Bonsai 27B needs about 7.8 GB of memory at Q2_0 (a 7.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 1.9 GB (Q4_1) to 53.8 GB (F16).
Ternary Bonsai 27B – 27B‑class reasoning in ternary transformer weights
Ternary Bonsai 27B is a GGUF model derived from Qwen3.6‑27B. It supports vision and language with a 262,144‑token context. The model is available in multiple quantizations, including Q4_1 and Q2_0, and is compatible with llama.cpp on CUDA, Metal, and CPU.
Good at
- Vision and language tasks
- Low‑bit inference on laptops
- Hybrid‑attention with 4‑bit KV cache
Limits
- No high‑precision escape hatches
- Requires 262,144‑token context for full capability
- License is apache‑2.0
Best for
- On‑device inference on single GPUs
- Mobile‑class inference with 1‑bit companion
- Developer testing of vision‑enabled LLMs
Who it’s for. Developers and researchers who need a compact, vision‑enabled LLM that can run on standard laptops or single GPUs. The model is suitable for on‑device inference and low‑budget deployments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_1 | 1.9 GB | 2.5 GB | Fits | Get file → | |
| — | 7.2 GB | 7.7 GB | Tight | Get file → | |
| Q2_0 | 7.2 GB | 7.7 GB | Tight | Get file → | |
| BF16 | 7.3 GB | 7.8 GB | Tight | Get file → | |
| — | 7.6 GB | 8.1 GB | Too big | Get file → | |
| F16 | 53.8 GB | 54.4 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_1 quantization (1.95 GB file, ~2.5 GB memory at 8 k context). For 16 GB VRAM, the Q2_0 quantization (7.17 GB file, ~7.8 GB memory) is appropriate. The BF16 and F16 variants require more memory and are not recommended for low‑budget setups.
What GPU do you need for Ternary Bonsai 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: the best quant that fits is Q4_1 (1.9 GB file, about 2.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (1.9 GB file, about 2.5 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (7.3 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (7.6 GB file, about 8.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (7.6 GB file, about 8.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (7.6 GB file, about 8.2 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (7.6 GB file, about 8.2 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (7.6 GB file, about 8.2 GB in use).
Which Ternary Bonsai 27B quant should you choose?
Q2_0 (7.2 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.
If memory is tight, the smallest file is Q4_1 at 1.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 27B
How much VRAM does Ternary Bonsai 27B need?
About 7.8 GB at Q2_0 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 27B on an 8 GB GPU?
Yes, with BF16: the 7.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ternary Bonsai 27B GGUF?
It depends on the quant: Q4_1 is 1.9 GB, file is 7.2 GB, Q2_0 is 7.2 GB, BF16 is 7.3 GB, file is 7.6 GB, F16 is 53.8 GB.
What context length does Ternary Bonsai 27B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.1 GB at 4K.
Where can I download Ternary Bonsai 27B GGUF?
The files are on Hugging Face in the prism-ml/Ternary-Bonsai-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 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 27B on 8 GB VRAM?
Yes, the Q4_1 quantization uses 1.95 GB file size and requires about 2.5 GB memory at 8 k context, which fits 8 GB VRAM.
Does the model support vision?
Yes, the model includes a vision encoder and is listed as having vision capability.
What license applies to this model?
The model is released under the apache‑2.0 license.