Ternary Bonsai 2 24B PTQ1 0 needs about 7.7 GB of memory at its main file (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
24B parameter ternary transformer for reasoning
Ternary Bonsai 2 24B PTQ1 0 is a 23.9B parameter model pruned from the 27B parent. It uses PTQ1_0 ternary quantization and supports 262144 token context. The model runs on the PrismML fork of llama.cpp.
Good at
- Reasoning
- Tool usage
- Large context
Limits
- Requires PrismML llama.cpp fork
- No vision support
- Only one quant file
Best for
- On‑device reasoning tasks
- Tool‑enabled agents
- Low‑memory inference
Who it’s for. Developers needing a compact reasoning model that fits on a 6‑GB GPU. It is suitable for applications where full FP16 is too large but high‑quality reasoning is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 5.3 GB | 7.7 GB | Tight | Get file → |
The only available quant is PTQ1_0. It is 5.27 GB and requires 7.7 GB VRAM at 8 k context. For 8 GB VRAM, it fits with a small host RAM buffer. No other quants are provided.
What GPU do you need for Ternary Bonsai 2 24B PTQ1 0?
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: the best quant that fits is the main file (5.3 GB file, about 7.7 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 2 24B PTQ1 0
How much VRAM does Ternary Bonsai 2 24B PTQ1 0 need?
About 7.7 GB at its main file with an 8K context window. That is the 5.3 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 24B PTQ1 0 on an 8 GB GPU?
Yes, with the smaller files: the 5.3 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ternary Bonsai 2 24B PTQ1 0 GGUF?
It depends on the quant: file is 5.3 GB.
What context length does Ternary Bonsai 2 24B PTQ1 0 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.
Where can I download Ternary Bonsai 2 24B PTQ1 0 GGUF?
The files are on Hugging Face in the henceiusegentoo/Ternary-Bonsai-2-24B-PTQ1_0-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 24B PTQ1 0 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 a 6 GB GPU?
Yes, the 5.27 GB size allows full GPU offloading on a 6 GB VRAM GPU with the PrismML llama.cpp fork.
Does it support vision?
No, the vision tower is separate and not included in this pack.
What license does it use?
The model is released under the apache-2.0 license.