TE

Bonsai-27B

TernaryGGUF by Hikari07jpUpdated 2026-07-22
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureqwen35
Smallest quant7.2 GB
Quick answer

Bonsai-27B needs about 9.8 GB of memory at Q2_0 (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

27B‑class reasoning in ternary weights, 7.2 GB GGUF file

Bonsai‑27B is a 27 billion‑parameter model quantized to Q2_0_g128. It offers 262 K‑token context and retains about 95 % of FP16 intelligence. The model runs on llama.cpp with hybrid‑attention kernels and includes a DSpark speculative‑decode drafter.

Good at

  • Large context (262 K tokens)
  • High‑quality reasoning and coding
  • Low‑bit ternary representation

Limits

  • Requires ~9.8 GB VRAM at 8 k context
  • No vision support
  • License is Apache‑2.0

Best for

  • Local offline assistants
  • Research on low‑bit models
  • Deploying on single GPU laptops

Who it’s for. Engineers and researchers who need a 27 B‑class model that fits on a single GPU or a laptop. The model is suitable for offline inference and experimentation with low‑bit ternary quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_07.2 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use the Q2_0_g128 file (7.17 GB). The estimated VRAM usage is about 9.8 GB at 8 k context, so it is borderline but feasible on high‑end GPUs. If VRAM is limited, consider the 1‑bit companion (~3.9 GB).

What GPU do you need for Bonsai-27B?

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 Q2_0 (7.2 GB file, about 9.8 GB in use).

Which Bonsai-27B quant should you choose?

Q2_0 (7.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byHikari07jp
FamilyTernary
Licenseapache-2.0
Downloads (HF)6,871
Last updated2026-07-22

Frequently asked questions about Bonsai-27B

How much VRAM does Bonsai-27B need?

About 9.8 GB at Q2_0 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 Bonsai-27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bonsai-27B GGUF?

It depends on the quant: Q2_0 is 7.2 GB.

What context length does Bonsai-27B 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 Bonsai-27B GGUF?

The files are on Hugging Face in the Hikari07jp/Ternary-Bonsai-27B-Abliterated-LowDeg-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 Bonsai-27B 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 Bonsai‑27B on 8 GB VRAM?

The Q2_0_g128 file requires roughly 9.8 GB VRAM at 8 k context, so it is close to the limit. A higher‑end GPU or lower context length may be needed.

Does Bonsai‑27B support vision?

No, the model only includes a 4‑bit vision tower in a separate companion; the main GGUF file is text‑only.

What license applies to Bonsai‑27B?

The model is released under the Apache‑2.0 license.

Other GGUFs of Ternary-Bonsai-27B-gguf

Similar models

Browse all →

More from Hikari07jp

All by Hikari07jp →

More Ternary models

All Ternary →

Other medium models

All medium models →