TE

Ternary Bonsai 4B

TernaryGGUF by prism-mlUpdated 2026-06-10
Download on Hugging Face
Parameters4B
Context32K
Layers36
Architectureqwen3
Smallest quant1.1 GB
Quick answer

Ternary Bonsai 4B needs about 2.8 GB of memory at Q2_0 (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.1 GB to 8.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Ternary Bonsai 4B – a 4‑billion‑parameter Qwen3 model in GGUF Q2_0 format

Ternary Bonsai 4B is a 4 billion‑parameter Qwen3 model released under Apache‑2.0. It is available in GGUF Q2_0 format for llama.cpp and an FP16 safetensors version for HuggingFace tooling. The model supports a 32 768‑token context window.

Good at

  • Large context handling
  • Low‑bit quantization for efficient inference
  • Compatibility with llama.cpp

Limits

  • No vision support
  • Requires custom llama.cpp fork for Q2_0
  • Limited to 32 768‑token context

Best for

  • Running on edge devices with limited VRAM
  • Serving lightweight inference services
  • Educational demos of low‑bit models

Who it’s for. Developers and researchers who need a compact Qwen3 model for CPU or Apple Silicon inference. The model is suitable for those who prefer open‑source tooling and can use the Prism fork of llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.1 GB 2.8 GB
Fits Get file →
Q2_01.1 GB 2.8 GB
Fits Get file →
Q2_01.1 GB 2.8 GB
Fits Get file →
F168.0 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use the Q2_0 GGUF file (1.07 GB) which requires about 2.8 GB of VRAM at 8 k context. If more VRAM is available, the FP16 file (8.05 GB) needs roughly 9.8 GB of VRAM. The unknown quant file has the same size as Q2_0 and similar memory usage.

What GPU do you need for Ternary Bonsai 4B?

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 (1.1 GB file, about 2.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q2_0 (1.1 GB file, about 2.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_0 (1.1 GB file, about 2.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.0 GB file, about 9.8 GB in use).

Which Ternary Bonsai 4B quant should you choose?

Q2_0 (1.1 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.

If memory is tight, the smallest file is the first one in the table at 1.1 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

Architectureqwen3
Parameters4B
Layers36
Trained context32,768 tokens
KV cache (fp16)144 KB per token

Source

Quantized byprism-ml
FamilyTernary
Licenseapache-2.0
Downloads (HF)6,182
Last updated2026-06-10

Frequently asked questions about Ternary Bonsai 4B

How much VRAM does Ternary Bonsai 4B need?

About 2.8 GB at Q2_0 with an 8K context window. That is the 1.1 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 4B on an 8 GB GPU?

Yes, with Q2_0: the 1.1 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ternary Bonsai 4B GGUF?

It depends on the quant: file is 1.1 GB, Q2_0 is 1.1 GB, Q2_0 is 1.1 GB, F16 is 8.0 GB.

What context length does Ternary Bonsai 4B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Ternary Bonsai 4B GGUF?

The files are on Hugging Face in the prism-ml/Ternary-Bonsai-4B-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 4B 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 4B on 8 GB VRAM?

Yes, the Q2_0 GGUF file is 1.07 GB and requires about 2.8 GB of VRAM at 8 k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

Which llama.cpp branch supports Q2_0?

Use the PrismML-Eng/llama.cpp fork on the prism branch, which adds Q2_0 support.

Other GGUFs of Ternary-Bonsai-4B-unpacked

Similar models

Browse all →

More from prism-ml

All by prism-ml →

More Ternary models

All Ternary →

Other small models

All small models →