Bonsai 2 27B GSQ RCO needs about 9.1 GB of memory at its main file (a 6.5 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 8.6 GB.
Bonsai 2 27B GSQ RCO – a 27B Qwen model with ternary GSQ and RCO quantization
Bonsai 2 27B GSQ RCO is a 27B parameter Qwen model refined with full-model ternary GSQ and task-loss RCO. It supports vision and language tasks and is released under the Apache‑2.0 license. The GGUF file is 6.5 GB and requires about 9.1 GB of VRAM at 8 k context.
Good at
- Vision‑language understanding
- Long‑horizon agentic tasks
- Coding and professional work
Limits
- Requires 9.1 GB VRAM at 8 k context
- No official vision‑language API support
- Apache‑2.0 license restricts commercial use without compliance
Best for
- Deploying on GPUs with ≥10 GB VRAM
- Research on vision‑language models
- Fine‑tuning for specific agentic workflows
Who it’s for. Researchers and developers needing a dense Qwen model with vision support and a permissive license. It is suitable for environments where 10 GB+ VRAM is available and custom fine‑tuning is desired.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 6.5 GB | 9.1 GB | Too big | Get file → |
The only available GGUF file is 6.5 GB with unknown quant. It needs about 9.1 GB VRAM at 8 k context. For 8 GB VRAM, it will not fit. If you have ≥10 GB VRAM, this file is suitable. No other quants are provided.
What GPU do you need for Bonsai 2 27B GSQ RCO?
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 (6.5 GB file, about 9.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Bonsai 2 27B GSQ RCO
How much VRAM does Bonsai 2 27B GSQ RCO need?
About 9.1 GB at its main file with an 8K context window. That is the 6.5 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 GSQ RCO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Bonsai 2 27B GSQ RCO GGUF?
It depends on the quant: file is 6.5 GB.
What context length does Bonsai 2 27B GSQ RCO 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 Bonsai 2 27B GSQ RCO GGUF?
The files are on Hugging Face in the ProCreations/bonsai-2-27b-gsq-rco-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 GSQ RCO 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 model requires about 9.1 GB VRAM at 8 k context, which exceeds 8 GB.
Does this model support vision tasks?
Yes. It is a causal language model with a vision encoder and supports image and video understanding.
What license does it use?
Apache‑2.0, which allows modification and redistribution with attribution.