prism-ml/Ternary-Bonsai-4B-unpacked
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: prism-ml/Ternary-Bonsai-4B-unpacked
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-27 14:49:15 +08:00
commit b21b6629cd
16 changed files with 152568 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
README.md Normal file
View File

@@ -0,0 +1,17 @@
---
license: apache-2.0
tags:
- prismml
- bonsai
- ternary
---
# Ternary-Bonsai-4B — Unpacked FP16 Safetensors
FP16 safetensors (HuggingFace format) of the ternary Bonsai-4B model. This repo exists for users who want to run Ternary Bonsai with stock HuggingFace tooling or frameworks that don't yet support any of the packed ternary format. The MLX 2-bit format is currently the only packed format available; more formats for other backends are coming soon.
> **We strongly recommend using the natively packed models instead.** The packed format is where all the benefits of Bonsai come from — up to 9x memory reduction, 5x faster inference, and lower energy per token. This unpacked FP16 version is full-size and does not provide any of those advantages.
For the optimized ternary release model (recommended):
- **[Ternary-Bonsai-4B MLX 2-bit](https://huggingface.co/prism-ml/Ternary-Bonsai-4B-mlx-2bit)** — Ternary MLX for Apple Silicon