QW

Ternary-Bonsai-2-2B

QwenGGUF by suryatmodulusUpdated 2026-10-16
Download on Hugging Face
Parameters1.88B
Context256K
Layers24
Architectureqwen35
Smallest quant0.4 GB
Quick answer

Ternary-Bonsai-2-2B needs about 1.4 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 3 quants, from 0.4 GB to 0.5 GB (Q2_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Ternary-Bonsai-2-2B: 2B‑parameter vision‑language model in GGUF format

Ternary-Bonsai-2-2B is a 1.88B parameter Qwen3.5‑2B derivative with ternary transformer weights. It supports vision input via a separate mmproj pack and offers a 262144‑token context window. The model is available in three GGUF packings: PTQ1_0 (0.43 GB), PQ2_0 (0.52 GB) and Q2_0 (0.55 GB).

Good at

  • Vision‑language reasoning
  • Tool usage
  • Multimodal inference

Limits

  • No Mixture‑of‑Experts
  • License: apache‑2.0
  • Requires separate mmproj for vision

Best for

  • Prototyping multimodal apps
  • Fine‑tuning on small datasets
  • Research on ternary quantization

Who it’s for. Developers and researchers needing a compact vision‑language model for prototyping or fine‑tuning. The model is suitable for environments with limited GPU memory and for experiments with ternary quantization techniques.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 1.3 GB
Fits Get file →
—0.5 GB 1.4 GB
Fits Get file →
Q2_00.5 GB 1.4 GB
Fits Get file →

For 8 GB VRAM, the 0.43 GB PTQ1_0 or 0.52 GB PQ2_0 packings are recommended, each estimating 1.3–1.4 GB memory at 8 k context. If a slightly larger memory budget is available, the 0.55 GB Q2_0 packing can be used, also estimating 1.4 GB memory at 8 k context. All estimates are approximate.

What GPU do you need for Ternary-Bonsai-2-2B?

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 Q2_0 (0.5 GB file, about 1.4 GB in use).

Which Ternary-Bonsai-2-2B quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters1.88B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bysuryatmodulus
FamilyQwen
Base modelQwen/Qwen3.5-2B
Licenseapache-2.0
Downloads (HF)690
Last updated2026-10-16

Frequently asked questions about Ternary-Bonsai-2-2B

How much VRAM does Ternary-Bonsai-2-2B need?

About 1.4 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 Ternary-Bonsai-2-2B on an 8 GB GPU?

Yes, with Q2_0: the 0.5 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ternary-Bonsai-2-2B GGUF?

It depends on the quant: file is 0.4 GB, file is 0.5 GB, Q2_0 is 0.5 GB.

What context length does Ternary-Bonsai-2-2B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Ternary-Bonsai-2-2B GGUF?

The files are on Hugging Face in the suryatmodulus/Ternary-Bonsai-2-2B-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 Ternary-Bonsai-2-2B 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‑2‑2B on 8 GB VRAM?

Yes. The 0.43 GB PTQ1_0 or 0.52 GB PQ2_0 packings use about 1.3–1.4 GB memory at 8 k context, well within an 8 GB VRAM budget.

Does the model support vision input?

Yes. Vision is handled by a separate mmproj pack that loads only when an image is provided.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Qwen3.5-2B

Similar models

Browse all →

More from suryatmodulus

All by suryatmodulus →

More Qwen models

All Qwen →

Other tiny models

All tiny models →