Bonsai-1.7B needs about 1.7 GB of memory at Q1_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB (Q1_0) to 0.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Bonsai-1.7B – 1‑bit Qwen3 model for low‑memory inference
Bonsai-1.7B is a 1.7 B parameter Qwen3 model quantized to 1‑bit (Q1_0). The GGUF file is 0.25 GB and requires about 1.7 GB of VRAM at 8 k context. It is released under Apache‑2.0 and supports cross‑platform inference via llama.cpp and MLX.
Good at
- 1‑bit inference on modest GPUs
- Fast generation on RTX 4090
- Runs on any device with llama.cpp
Limits
- Requires 8 k context or larger
- No vision or multimodal support
- Only 1‑bit Q1_0 quant available
Best for
- Edge device inference
- Low‑cost cloud deployments
- Rapid prototyping with minimal VRAM
Who it’s for. Developers needing a small, fast language model for local deployment. Ideal for projects where memory budget is tight and inference speed is important.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q1_0 | 0.2 GB | 1.7 GB | Fits | Get file → | |
| — | 0.2 GB | 1.7 GB | Fits | Get file → |
For 8 GB VRAM, use the Q1_0 GGUF (0.25 GB on disk, ~1.7 GB RAM). If you have 4 GB VRAM, the model will not fit due to the 1.7 GB requirement. No other quants are available.
What GPU do you need for Bonsai-1.7B?
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 Q1_0 (0.2 GB file, about 1.7 GB in use).
Which Bonsai-1.7B quant should you choose?
Q1_0 (0.2 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 Bonsai-1.7B
How much VRAM does Bonsai-1.7B need?
About 1.7 GB at Q1_0 with an 8K context window. That is the 0.2 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-1.7B on an 8 GB GPU?
Yes, with Q1_0: the 0.2 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Bonsai-1.7B GGUF?
It depends on the quant: Q1_0 is 0.2 GB, file is 0.2 GB.
What context length does Bonsai-1.7B 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-1.7B GGUF?
The files are on Hugging Face in the prism-ml/Bonsai-1.7B-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-1.7B 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 Bonsai-1.7B on 8 GB VRAM?
Yes, the Q1_0 quant uses about 1.7 GB of VRAM at 8 k context, well within an 8 GB budget.
Does Bonsai-1.7B support vision tasks?
No, it is a pure language model with no vision or multimodal capabilities.