Bonsai 2 27B PQ2 0 MTP needs about 10.2 GB of memory at its main file (a 7.6 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 8.7 GB.
Bonsai 2 27B PQ2 0 MTP – a 27.3B Qwen3.5 model with multi‑token‑prediction head
Bonsai 2 27B PQ2 0 MTP is a 27.3B parameter model based on the qwen35 architecture. It supports reasoning and tool use, and is released under Apache‑2.0. The model uses a multi‑token‑prediction head for speculative decoding.
Good at
- Reasoning
- Tool use
- Speculative decoding
Limits
- No vision support
- Requires patched llama.cpp for draft‑mtp
- Estimated 10.2 GB VRAM at 8 k context
Best for
- Chatbot reasoning tasks
- Tool‑integrated workflows
- Speculative decoding experiments
Who it’s for. Developers and researchers who need a large language model with reasoning and tool‑use capabilities, and who can run it on GPUs with at least 10 GB VRAM and a patched llama.cpp build.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 7.6 GB | 10.2 GB | Too big | Get file → |
The available GGUF file is unquantized (unknown quant). It is 7.56 GB and requires about 10.2 GB VRAM at 8 k context. For lower memory budgets, a quantized version would be needed, but none is provided here.
What GPU do you need for Bonsai 2 27B PQ2 0 MTP?
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 (7.6 GB file, about 10.2 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Bonsai 2 27B PQ2 0 MTP
How much VRAM does Bonsai 2 27B PQ2 0 MTP need?
About 10.2 GB at its main file with an 8K context window. That is the 7.6 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 2 27B PQ2 0 MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Bonsai 2 27B PQ2 0 MTP GGUF?
It depends on the quant: file is 7.6 GB.
What context length does Bonsai 2 27B PQ2 0 MTP support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Bonsai 2 27B PQ2 0 MTP GGUF?
The files are on Hugging Face in the groxaxo/Bonsai-2-27B-PQ2_0-MTP-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 2 27B PQ2 0 MTP 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?
No. The estimated VRAM requirement is 10.2 GB at 8 k context.
Does this model support vision?
No, it has no vision capabilities.
Do I need a patched llama.cpp to use draft‑mtp?
Yes, the stock binary fails at startup; a patch is required.