prism-ml/Ternary-Bonsai-2-27B-gguf-dev overview
Bonsai 2 27B, Q2 0 testing build The Q2 0 packing of Bonsai 2 27B, kept separate until upstream support lands. Bonsai 2 needs an activation transform that curr…
Runs locally from ~7.10 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Ternary-Bonsai-2-27B-Q2_0-prism-fork-required.gguf | GGUF | Q2_0 | 7.10 GB | Download |
Model Details
| Model ID | prism-ml/Ternary-Bonsai-2-27B-gguf-dev |
|---|---|
| Author | prism-ml |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | Qwen/Qwen3.8-27B |
| Last modified | 2026-09-17T18:44:02.000Z |
Model README
---
license: apache-2.0
library_name: llama.cpp
pipeline_tag: text-generation
tags:
- ternary
- 2-bit
- gguf
- llama-cpp
- prismml
- bonsai
base_model:
- Qwen/Qwen3.8-27B
---
Bonsai 2 27B, Q2_0 (testing build)
The Q2_0 packing of Bonsai 2 27B, kept separate until upstream support lands.
Bonsai 2 needs an activation transform that currently only exists in our
llama.cpp fork. Stock llama.cpp will load this file
anyway, since it knows the Q2_0 type and the qwen35 architecture, and outputs gibberish with no
warning. The main repo's PQ2_0 and PTQ1_0 use types stock llama.cpp does not know, so it stops
with an error rather than running them. That is why they ship there and this one does not.
It is here for testing, kernel work, and upstreaming. It moves to the main repo once that lands.
For normal use:
Ternary-Bonsai-2-27B-mlx-2bit on
Apple Silicon. Setup for every backend:
contact@prismml.com
Run prism-ml/Ternary-Bonsai-2-27B-gguf-dev with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models