Bonsai 27B antidoom 1bit DSpark needs about 2.4 GB of memory at Q4_1 (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.8 GB (Q4_1) to 4.7 GB (Q1_0).
Bonsai 27B antidoom 1bit DSpark – 1‑bit transformer with 262K‑token context
Bonsai 27B antidoom 1bit DSpark is a 26.9B‑parameter model quantized to 1‑bit weights. It supports reasoning, tools, and vision, and runs on llama.cpp with custom 1‑bit hybrid‑attention kernels. The model offers a 262K‑token context window and a 1.37× decode speedup on CUDA.
Good at
- 1‑bit reasoning with high accuracy
- 262K‑token on‑device context
- CUDA and Metal inference
Limits
- No high‑precision escape hatches
- Requires custom llama.cpp fork
- Vision tower is 4‑bit HQQ
Best for
- Low‑memory inference on laptops
- Rapid speculative decoding
- Embedded device inference
Who it’s for. Developers needing a compact 27B model for on‑device reasoning and vision tasks. Suitable for users with limited GPU memory who can run custom llama.cpp kernels.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_1 | 1.8 GB | 2.3 GB | Fits | Get file → | |
| Q1_0 | 4.7 GB | 5.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_1 (1.79 GB file, ~2.4 GB memory at 8K context). For 16 GB VRAM, Q1_0 (4.67 GB file, ~5.3 GB memory at 8K context) offers higher fidelity.
What GPU do you need for Bonsai 27B antidoom 1bit DSpark?
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 Q4_1 (1.8 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is Q1_0 (4.7 GB file, about 5.3 GB in use).
Which Bonsai 27B antidoom 1bit DSpark quant should you choose?
Q4_1 (1.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Bonsai 27B antidoom 1bit DSpark
How much VRAM does Bonsai 27B antidoom 1bit DSpark need?
About 2.4 GB at Q4_1 with an 8K context window. That is the 1.8 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 27B antidoom 1bit DSpark on an 8 GB GPU?
Yes, with Q1_0: the 4.7 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Bonsai 27B antidoom 1bit DSpark GGUF?
It depends on the quant: Q4_1 is 1.8 GB, Q1_0 is 4.7 GB.
What context length does Bonsai 27B antidoom 1bit DSpark support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.1 GB at 4K.
Where can I download Bonsai 27B antidoom 1bit DSpark GGUF?
The files are on Hugging Face in the Danny-Dasilva/Bonsai-27B-antidoom-1bit-DSpark 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 27B antidoom 1bit DSpark 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 27B antidoom 1bit DSpark on 8 GB VRAM?
Yes, the Q4_1 quantization uses about 2.4 GB of VRAM at 8K context, fitting within 8 GB.
Does the model support vision tasks?
Yes, it includes a 4‑bit HQQ vision tower, but the main model is 1‑bit for language.
What license applies to this model?
The model is released under the apache-2.0 license.