TE

Ternary Bonsai 2 27B Abliterated PQ2 0 MTP

TernaryGGUF by BoldingBuildsUpdated 2026-09-26
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureqwen35
Smallest quant7.2 GB
Quick answer

Ternary Bonsai 2 27B Abliterated PQ2 0 MTP needs about 9.9 GB of memory at its main file (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.2 GB to 7.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

27B ternary transformer with 262K‑token context, 7.21 GB GGUF

Ternary Bonsai 2 27B Abliterated PQ2 0‑MTP is a 27 billion‑parameter model quantized to ternary weights. It offers 262 K‑token context and retains 98.2 % of FP16 intelligence. The model is released under Apache‑2.0 and runs on llama.cpp, Metal, CUDA, and MLX.

Good at

  • Large‑context reasoning
  • Fast speculative decoding
  • Low‑bit inference

Limits

  • No vision support
  • Requires 8 GB+ VRAM for PQ2 0
  • License is Apache‑2.0

Best for

  • Long‑form text generation
  • On‑device reasoning tasks
  • Low‑memory inference

Who it’s for. Developers needing a 27 B model that fits on a single GPU or laptop. The model is suitable for applications that require extended context and efficient low‑bit inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.2 GB 9.9 GB
Too big Get file →
—7.7 GB 10.3 GB
Too big Get file →

For 8 GB VRAM, use the 7.21 GB PQ2 0 file (≈10.3 GB RAM at 8 K context). If memory is tighter, the 7.66 GB file uses slightly more RAM but offers the same performance. Both files are identical in language weights; the MTP file adds speculative decoding support.

What GPU do you need for Ternary Bonsai 2 27B Abliterated PQ2 0 MTP?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (7.7 GB file, about 10.3 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters27B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byBoldingBuilds
FamilyTernary
Licenseapache-2.0
Downloads (HF)9,456
Last updated2026-09-26

Frequently asked questions about Ternary Bonsai 2 27B Abliterated PQ2 0 MTP

How much VRAM does Ternary Bonsai 2 27B Abliterated PQ2 0 MTP need?

About 9.9 GB at its main file with an 8K context window. That is the 7.2 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 Abliterated PQ2 0 MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ternary Bonsai 2 27B Abliterated PQ2 0 MTP GGUF?

It depends on the quant: file is 7.2 GB, file is 7.7 GB.

What context length does Ternary Bonsai 2 27B Abliterated PQ2 0 MTP support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Ternary Bonsai 2 27B Abliterated PQ2 0 MTP GGUF?

The files are on Hugging Face in the BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PQ2_0-MTP-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 Abliterated PQ2 0 MTP 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 7.21 GB PQ2 0 file requires about 10.3 GB RAM at 8 K context, which fits on an 8 GB GPU with some headroom.

Does the model support vision?

No, the vision tower is shipped separately as a Q8_0 mmproj pack and is not included in this GGUF.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing commercial use and modification.

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

Similar models

Browse all →

More from BoldingBuilds

All by BoldingBuilds →

More Ternary models

All Ternary →

Other medium models

All medium models →