Sakura Micro Bonsai 2 GSQ RCO needs about 8.3 GB of memory at TQ1_0 (a 5.7 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.
Sakura Micro Bonsai 2 GSQ-RCO – ultra‑low‑bit 27B model
Sakura Micro Bonsai 2 GSQ-RCO is a 27B‑parameter model derived from Prism ML's Ternary Bonsai 2. It uses GSQ/RCO mixed‑codec compression and a ternary quantization type TQ1_0. The model retains reasoning and agentic behavior while fitting into a 5.69 GB GGUF file.
Good at
- 262 K‑token context
- Ultra‑low‑bit inference
- Ternary weight efficiency
Limits
- No vision support
- Requires llama.cpp or compatible runtime
- Experimental release
Best for
- On‑device reasoning
- Low‑memory inference
- Fine‑tuning on small GPUs
Who it’s for. Developers needing a 27B‑class model that fits on a single GPU or laptop with limited VRAM. Ideal for research or edge deployment where memory is constrained.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 5.7 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM, the TQ1_0 quantization (5.69 GB file, ~8.3 GB memory at 8 k context) is suitable. If more memory is available, consider larger quantizations for faster inference, but they are not listed here.
What GPU do you need for Sakura Micro Bonsai 2 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 TQ1_0 (5.7 GB file, about 8.3 GB in use).
Which Sakura Micro Bonsai 2 GSQ RCO quant should you choose?
TQ1_0 (5.7 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sakura Micro Bonsai 2 GSQ RCO
How much VRAM does Sakura Micro Bonsai 2 GSQ RCO need?
About 8.3 GB at TQ1_0 with an 8K context window. That is the 5.7 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 Sakura Micro Bonsai 2 GSQ RCO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Sakura Micro Bonsai 2 GSQ RCO GGUF?
It depends on the quant: TQ1_0 is 5.7 GB.
What context length does Sakura Micro Bonsai 2 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 Sakura Micro Bonsai 2 GSQ RCO GGUF?
The files are on Hugging Face in the webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Sakura Micro Bonsai 2 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 Sakura Micro Bonsai 2 GSQ-RCO on 8 GB VRAM?
Yes, the TQ1_0 quantization requires approximately 8.3 GB VRAM at 8 k context, which fits within an 8 GB GPU with some overhead.
Does this model support vision tasks?
No, the vision tower is shipped separately and not included in this GGUF file.
What license applies to this model?
The model is licensed under Apache‑2.0, as stated in the model card.