Downloads · 30 days
9
4% of all-time downloads
Bonsai-8B-TRNQ
Trillim/Bonsai-8B-TRNQ
Bonsai-8B-TRNQ is a text generation model from Trillim. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Bonsai-8B-TRNQ is a Trillim-packaged, requantized build of prism-ml/Bonsai-8B-unpacked, intended for efficient text generation with the Trillim inference engine.
All-time downloads
242
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tensors1.2 GB · 93%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Apr 9, 2026
- Updated
- Apr 17, 2026
- SHA
- 6e4bf93c
Try a prompt
Base models
Model card
From the Hugging Face model README
Bonsai-8B-TRNQ
Bonsai-8B-TRNQ is a Trillim-packaged, requantized build of prism-ml/Bonsai-8B-unpacked, intended for efficient text generation with the Trillim inference engine.
Overview
- Based on Prism ML’s Bonsai-8B release
- Requantized and packaged for Trillim runtime
- Includes tokenizer, chat template, and Trillim-specific runtime artifacts
- Distributed under the upstream Apache 2.0 license with attribution preserved
Model Details
| Item | Value |
|---|---|
| Architecture | Qwen3-8B dense |
| Parameters | 8B class |
| Source model | prism-ml/Bonsai-8B-unpacked |
| Packaging | Trillim requantized bundle |
| License | Apache 2.0 |
Usage
pip install trillim
trillim pull Trillim/Bonsai-8B-TRNQ
trillim chat Trillim/Bonsai-8B-TRNQ
This launches an interactive CLI chat session.
Repository Contents
| File | Description |
|---|---|
qmodel.tensors | Quantized weights in Trillim format |
rope.cache | Precomputed RoPE cache for runtime |
config.json | Model configuration |
generation_config.json | Generation defaults |
trillim_config.json | Trillim runtime metadata |
tokenizer.json | Tokenizer data |
tokenizer_config.json | Tokenizer configuration |
special_tokens_map.json | Special token mapping |
chat_template.jinja | Chat template |
vocab.json, merges.txt, added_tokens.json | Tokenizer assets |
Provenance
This repository is derived from:
prism-ml/Bonsai-8B-unpacked- Qwen3-8B by Alibaba Cloud
Changes made by Trillim:
- Requantized from the upstream release
- Repackaged for the Trillim inference engine
This repository is not affiliated with or endorsed by Prism ML or Alibaba Cloud.
License
Released under the Apache 2.0 License, consistent with the upstream model license.
See:
LICENSENOTICE.txt
- Task
- Text Generation
- Type
- qwen3
- License
- apache-2.0
- Created
- Apr 9, 2026
- Updated
- Apr 17, 2026