Downloads · 30 days
17.7K
49% of all-time downloads
Bonsai-8B-unpacked
prism-ml/Bonsai-8B-unpacked
Bonsai-8B-unpacked is a machine learning model from prism-ml. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
FP16 safetensors (HuggingFace format) of the 1-bit Bonsai-8B model. This repo exists for users who want to run Bonsai with stock HuggingFace tooling or frameworks that don't yet support 1-bit weights natively. The 1-b…
All-time downloads
36.3K
Public
Parameters
8.2B
16.4 GB on disk
Likes
17
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Mar 24, 2026
- Updated
- Apr 16, 2026
- SHA
- 376f3815
Model card
From the Hugging Face model README
Bonsai-8B — Unpacked FP16 Safetensors
FP16 safetensors (HuggingFace format) of the 1-bit Bonsai-8B model. This repo exists for users who want to run Bonsai with stock HuggingFace tooling or frameworks that don't yet support 1-bit weights natively. The 1-bit kernels are currently in our forks of MLX and llama.cpp — once they land upstream, this unpacked version will no longer be needed.
We strongly recommend using the native 1-bit models instead. The 1-bit format is where all the benefits of Bonsai come from — up to 14x memory reduction, 6x faster inference, and 5x lower energy per token. This unpacked FP16 version is full-size and does not provide any of those advantages.
For the optimized 1-bit release models (recommended):
- Bonsai-8B GGUF Q1_0 — 1-bit GGUF for llama.cpp (CUDA, Metal, CPU)
- Bonsai-8B MLX 1-bit — 1-bit MLX for Apple Silicon
- Type
- qwen3
- License
- apache-2.0
- Created
- Mar 24, 2026
- Updated
- Apr 16, 2026