TE

Bonsai JEV

TernaryGGUF by dakebakeryUpdated 2026-10-17
Download on Hugging Face
Parameters26.9B
Context—
Layers—
Architectureqwen35
Smallest quant0.2 GB
Quick answer

Bonsai JEV needs about 1.0 GB of memory at its main file (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.2 GB (F16) to 7.2 GB.

27B decision model with ternary weights, fits on 8 GB GPU

Bonsai JEV is a 26.9 B parameter model built on Ternary Bonsai 2 27B. It delivers calibrated yes/no or multi‑choice decisions with image input, without generating text. The model is released under Apache 2.0 and runs on llama.cpp.

Good at

  • Fast decision inference
  • Calibrated probability outputs
  • Image‑enabled yes/no queries

Limits

  • 262K‑token context
  • Requires at least 8 GB VRAM for full model
  • No text generation

Best for

  • Rapid decision APIs
  • Low‑latency inference on laptops
  • Image‑based classification tasks

Who it’s for. Developers who need a lightweight decision engine for applications that require image input and calibrated probabilities, but not text generation. The model is suitable for edge deployment and integration into existing systems via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.2 GB 0.8 GB
Fits Get file →
—0.5 GB 1.0 GB
Fits Get file →
—5.9 GB 7.2 GB
Fits Get file →
—7.2 GB 8.6 GB
Too big Get file →

For 8 GB VRAM use the F16 pack (0.23 GB, ~0.8 GB memory at 8 k context). If more memory is available, the 0.46 GB pack (~1 GB memory) or the 5.95 GB pack (~7.2 GB memory) can be used. The 7.21 GB pack (~8.6 GB memory) is the largest option.

What GPU do you need for Bonsai JEV?

These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (0.5 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (5.9 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 8.6 GB in use).

Which Bonsai JEV quant should you choose?

If memory is tight, the smallest file is F16 at 0.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters26.9B

Source

Quantized bydakebakery
FamilyTernary
Licenseapache-2.0
Downloads (HF)2,556
Last updated2026-10-17

Frequently asked questions about Bonsai JEV

How much VRAM does Bonsai JEV need?

About 1.0 GB at its main file with an 8K context window. That is the 0.5 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 JEV on an 8 GB GPU?

Yes, with the smaller files: the 5.9 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bonsai JEV GGUF?

It depends on the quant: F16 is 0.2 GB, file is 0.5 GB, file is 5.9 GB, file is 7.2 GB.

Where can I download Bonsai JEV GGUF?

The files are on Hugging Face in the dakebakery/Bonsai-JEV 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 JEV 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.

Does Bonsai JEV support text generation?

No, it only returns calibrated decision probabilities and does not generate text.

Is the model compatible with llama.cpp on CPU?

The model is designed for llama.cpp GPU backends; CPU usage is not supported in the provided builds.

Other GGUFs of Ternary-Bonsai-2-27B-gguf

Similar models

Browse all →

More Ternary models

All Ternary →

Other medium models

All medium models →