---

license: apache-2.0

library_name: llama.cpp

pipeline_tag: text-generation

tags:

- gguf

- text-generation

- chat

- ternary

- quantized

- on-device

- mirror

language:

- en

base_model: prism-ml/Ternary-Bonsai-1.7B-gguf

---

Model Card for Ternary Bonsai 1.7B (GGUF, mirror)

An unmodified mirror of one quant of Prism ML's Ternary Bonsai 1.7B GGUF. This is

a byte-for-byte copy re-hosted under the Apache 2.0 license as a stable pinned

snapshot that survives if the upstream repo is moved or removed. It is NOT the

authoritative source and adds nothing to the model.

This repository holds a single quantized weight file only, not training data or

original weights, and nothing here was re-quantized, converted, or otherwise

changed. For the full model card, benchmarks, other quants, and the whitepaper,

use the original repository.

Model Details

Model Description

Ternary Bonsai 1.7B is a dense Qwen3 model (general.architecture = qwen3):

grouped-query attention (GQA) with a SwiGLU MLP, RoPE, and RMSNorm across every

layer -- no Gated DeltaNet / linear-attention blocks (those belong to the 27B

hybrid). The weights are quantized to a true ternary alphabet {-1, 0, +1}

(~1.58 bits of information per weight). This mirror carries the Q2_0_g128

build: each 128-weight block is { FP16 scale d; 2-bit codes qs[32] } (34 bytes,

2.125 bits/weight effective) and dequantizes as w = (code - 1) * d.

• Developed by: Prism ML (model + ternary quantization), built from

Qwen3-1.7B by Alibaba Cloud; this repository is an unmodified mirror by leok7v

• Model type: Dense grouped-query-attention causal language model,

ternary-quantized GGUF (llama.cpp)

• Language(s): English and the languages of the base model
• License: Apache 2.0 (inherited unchanged from the upstream model)
• Mirrored from model:

prism-ml/Ternary-Bonsai-1.7B-gguf

Model Sources

• Repository (this mirror): https://huggingface.co/leok7v/Ternary-Bonsai-1.7B-gguf
• Original (authoritative) repository:

prism-ml/Ternary-Bonsai-1.7B-gguf

(Apache 2.0)

• Base model:

Qwen/Qwen3-1.7B (Apache 2.0)

• Q2_0 kernels: PrismML-Eng/llama.cpp

(prism branch) -- Q2_0 is not yet in mainline llama.cpp.

Attribution

> Created using Bonsai by Prism ML.

Copyright 2026-present Prism ML, Inc.; built from Qwen3-1.7B, Copyright 2026

Alibaba Cloud. Apache 2.0, inherited unchanged from upstream; see the original

repository for the full LICENSE / NOTICE.

Contents

| File | Notes |

| :--- | :--- |

| Ternary-Bonsai-1.7B-Q2_0.gguf (~442 MiB) | Byte-for-byte copy of the upstream Q2_0_g128 ternary build. |

Why a mirror and not a fork

Hugging Face does not support forking a model repository, so mirroring the weight

file is the only way to keep a pinned snapshot; the storage and bandwidth are the

mirror's cost, not upstream's. If you just want the model, prefer the original.