TE

Ternary Bonsai 2 9B Hf Bf16

TernaryGGUF by mradermacherUpdated 2026-10-17
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant2.9 GB
Quick answer

Ternary Bonsai 2 9B Hf Bf16 needs about 4.5 GB of memory at BF16 (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.9 GB (BF16) to 3.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Ternary Bonsai 2 9B Hf Bf16 – dense BF16 Qwen3.5 model

Ternary Bonsai 2 9B Hf Bf16 is a dense BF16 checkpoint of the Qwen3.5 architecture. It contains 8.95 billion parameters and supports reasoning, tools, and vision. The model is released under Apache 2.0.

Good at

  • Reasoning
  • Tool usage
  • Vision tasks

Limits

  • No mixture of experts
  • Large VRAM requirement
  • No custom code needed

Best for

  • Chatbot development
  • Code generation
  • Image captioning

Who it’s for. Developers needing a versatile Qwen3.5 model with vision support. The model is suitable for applications that can accommodate its memory footprint and do not require a mixture of experts.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF162.9 GB 4.5 GB
Fits Get file →
BF163.2 GB 4.8 GB
Fits Get file →

For 8 GB VRAM use the BF16 quant with file size 2.88 GB, which estimates 4.5 GB memory at 8k context. For 12 GB VRAM use the BF16 quant 3.21 GB, estimating 4.8 GB memory. Both are dense BF16 and compatible with transformers.

What GPU do you need for Ternary Bonsai 2 9B Hf Bf16?

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: the best quant that fits is BF16 (3.2 GB file, about 4.8 GB in use).

Which Ternary Bonsai 2 9B Hf Bf16 quant should you choose?

BF16 (2.9 GB) is the middle option in this repository. 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
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyTernary
Licenseapache-2.0
Downloads (HF)1,108
Last updated2026-10-17

Frequently asked questions about Ternary Bonsai 2 9B Hf Bf16

How much VRAM does Ternary Bonsai 2 9B Hf Bf16 need?

About 4.5 GB at BF16 with an 8K context window. That is the 2.9 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 9B Hf Bf16 on an 8 GB GPU?

Yes, with BF16: the 3.2 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ternary Bonsai 2 9B Hf Bf16 GGUF?

It depends on the quant: BF16 is 2.9 GB, BF16 is 3.2 GB.

What context length does Ternary Bonsai 2 9B Hf Bf16 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Ternary Bonsai 2 9B Hf Bf16 GGUF?

The files are on Hugging Face in the mradermacher/Ternary-Bonsai-2-9B-hf-bf16-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 9B Hf Bf16 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 this model on 8 GB VRAM?

Yes, the BF16 quant of 2.88 GB file size uses about 4.5 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

Yes, the model includes a vision tower and patch embedding, enabling vision capabilities.

What license applies to this model?

The model is released under Apache 2.0, matching the parent model and source pack.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ternary models

All Ternary →

Other small models

All small models →