Ternary Bonsai 2 27B gguf dev needs about 10.3 GB of memory at Q2_0 (a 7.6 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.
Ternary Bonsai 2 27B – a dense Qwen3.8‑based model in Q2_0 quant.
Ternary Bonsai 2 27B is a 27‑billion‑parameter dense model derived from Qwen3.8‑27B. It uses the qwen35 architecture and supports a 262,144‑token context window. The model is distributed under the Apache‑2.0 license and is available in a single Q2_0 quantized GGUF file.
Good at
- Large‑context language generation
- Dense model inference on limited VRAM
- Compatibility with llama.cpp and mlx backends
Limits
- Requires 10.3 GB VRAM at 8 k context (Q2_0)
- No vision‑language support in this quant
- License is Apache‑2.0 – no commercial restrictions
Best for
- Long‑form text completion
- Fine‑tuning on small datasets
- Running on mid‑range GPUs
Who it’s for. Developers needing a compact, high‑capacity Qwen3.8 model for local inference. The single Q2_0 quant file makes it suitable for environments with limited VRAM while still offering a large context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_0 | 7.6 GB | 10.3 GB | Too big | Get file → |
The only available quant is Q2_0, 7.63 GB on disk. It requires approximately 10.3 GB VRAM at 8 k context. For 8 GB VRAM users, this quant will not fit; consider using a larger quant or a different model. If you have 12 GB or more, Q2_0 is the recommended choice for the best balance of size and performance.
What GPU do you need for Ternary Bonsai 2 27B gguf dev?
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 Q2_0 (7.6 GB file, about 10.3 GB in use).
Which Ternary Bonsai 2 27B gguf dev quant should you choose?
Q2_0 (7.6 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ternary Bonsai 2 27B gguf dev
How much VRAM does Ternary Bonsai 2 27B gguf dev need?
About 10.3 GB at Q2_0 with an 8K context window. That is the 7.6 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 Ternary Bonsai 2 27B gguf dev on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ternary Bonsai 2 27B gguf dev GGUF?
It depends on the quant: Q2_0 is 7.6 GB.
What context length does Ternary Bonsai 2 27B gguf dev 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 Ternary Bonsai 2 27B gguf dev GGUF?
The files are on Hugging Face in the prism-ml/Ternary-Bonsai-2-27B-gguf-dev repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Ternary Bonsai 2 27B gguf dev 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 Ternary Bonsai 2 27B on 8 GB VRAM?
No. The Q2_0 quant requires about 10.3 GB VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision tasks?
The base model includes a vision encoder, but the Q2_0 quant is not configured for vision inference in this build.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.