Bonsai web needs about 2.6 GB of memory at Q1_0 (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.2 GB (Q1_0) to 3.8 GB (Q1_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Bonsai web is a 1.72B-parameter Qwen model in GGUF format, quantized by WaveCut. Its trained context length is 32K tokens. The repository has 5 quant files, from 0.2 GB (Q1_0) to 3.8 GB (Q1_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q1_0 | 0.2 GB | 1.7 GB | Fits | Get file → | |
| Q1_0 | 0.6 GB (2 parts) | 2.0 GB | Fits | Get file → | |
| Q1_0 | 1.2 GB (3 parts) | 2.6 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.3 GB | Fits | Get file → | |
| Q1_0 | 3.8 GB (8 parts) | 5.2 GB | Fits | Get file → |
What GPU do you need for Bonsai web?
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 Q8_0 (1.8 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q1_0 (3.8 GB file, about 5.2 GB in use).
Which Bonsai web quant should you choose?
Q1_0 (1.2 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is Q1_0 at 0.2 GB, with the quality trade-offs that come with fewer bits. 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 Bonsai web
How much VRAM does Bonsai web need?
About 2.6 GB at Q1_0 with an 8K context window. That is the 1.2 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 Bonsai web on an 8 GB GPU?
Yes, with Q1_0: the 3.8 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Bonsai web GGUF?
It depends on the quant: Q1_0 is 0.2 GB, Q1_0 is 0.6 GB, Q1_0 is 1.2 GB, Q8_0 is 1.8 GB, Q1_0 is 3.8 GB.
What context length does Bonsai web support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Bonsai web GGUF?
The files are on Hugging Face in the WaveCut/Bonsai-web-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 web 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.