TE

Ternary Bonsai 2 27B MTP drafter

TernaryGGUF by killy369Updated 2026-09-25
Download on Hugging Face
Parameters2.03B
Context256K
Layers65
Architectureqwen35
Smallest quant1.1 GB
Quick answer

Ternary Bonsai 2 27B MTP drafter needs about 3.7 GB of memory at its main file (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Ternary Bonsai 2 27B MTP drafter – 27B‑class reasoning in ternary weights

Ternary Bonsai 2 27B MTP drafter is a 2.03 billion‑parameter model built on the Ternary family and Qwen3.5 architecture. It offers 262,144‑token context and is quantized to a 1.06 GB GGUF file. The model is released under Apache‑2.0 and supports llama.cpp, CUDA, Metal, and MLX.

Good at

  • Large‑context reasoning
  • Fast speculative decoding with MTP draft head
  • Low‑bit ternary inference

Limits

  • No vision support
  • Requires Pascal patch for draft head
  • Only one quant available

Best for

  • Chatbots needing long context
  • On‑device reasoning on laptops
  • Speculative decoding pipelines

Who it’s for. Developers and researchers who need a 27B‑class model that fits on a single GPU or laptop and can run with low‑bit ternary kernels. The model is suitable for inference on llama.cpp, CUDA, Metal, and MLX backends.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.1 GB 3.7 GB
Fits Get file →

The only available quant is the 1.06 GB GGUF file with an estimated 3.7 GB VRAM requirement at 8 k context. This is the recommended pack for systems with at least 4 GB VRAM. No other quants are provided, so memory estimates are approximate.

What GPU do you need for Ternary Bonsai 2 27B MTP drafter?

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 the main file (1.1 GB file, about 3.7 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters2.03B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized bykilly369
FamilyTernary
Licenseapache-2.0
Downloads (HF)585
Last updated2026-09-25

Frequently asked questions about Ternary Bonsai 2 27B MTP drafter

How much VRAM does Ternary Bonsai 2 27B MTP drafter need?

About 3.7 GB at its main file 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 2 27B MTP drafter on an 8 GB GPU?

Yes, with the smaller files: the 1.1 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ternary Bonsai 2 27B MTP drafter GGUF?

It depends on the quant: file is 1.1 GB.

What context length does Ternary Bonsai 2 27B MTP drafter support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download Ternary Bonsai 2 27B MTP drafter GGUF?

The files are on Hugging Face in the killy369/Ternary-Bonsai-2-27B-MTP-drafter-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 27B MTP drafter 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 4 GB VRAM?

The 1.06 GB GGUF file requires about 3.7 GB VRAM at 8 k context, so it can run on a 4 GB GPU but may be close to the limit.

Does this model support vision?

No, the model does not include a vision tower; it is purely a language model.

What license does it use?

The model is released under the Apache‑2.0 license.

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

Similar models

Browse all →

More Ternary models

All Ternary →

Other tiny models

All tiny models →