model-00005-of-00012.safetensors 5.0 GBmodel-00008-of-00012.safetensors 5.0 GBmodel-00011-of-00012.safetensors 5.0 GBmodel-00003-of-00012.safetensors 5.0 GBmodel-00009-of-00012.safetensors 5.0 GBmodel-00010-of-00012.safetensors 4.9 GBmodel-00007-of-00012.safetensors 4.9 GBmodel-00006-of-00012.safetensors 4.9 GBmodel-00004-of-00012.safetensors 4.9 GBmodel-00002-of-00012.safetensors 4.8 GBmodel-00012-of-00012.safetensors 2.8 GBmodel-00001-of-00012.safetensors 2.5 GB| Parameter | Value |
|---|---|
| direction_index | 29.58 |
| attn.o_proj.max_weight | 1.43 |
| attn.o_proj.max_weight_position | 38.82 |
| attn.o_proj.min_weight | 0.91 |
| attn.o_proj.min_weight_distance | 23.43 |
| mlp.down_proj.max_weight | 1.39 |
| mlp.down_proj.max_weight_position | 39.20 |
| mlp.down_proj.min_weight | 1.38 |
| mlp.down_proj.min_weight_distance | 31.17 |
| Metric | This model | Original model (prism-ml/Bonsai-27B-unpacked) |
|---|---|---|
| KL divergence | 0.0033 | 0 (by definition) |
| Refusals | 6/100 | 81/100 |
FP16 safetensors (HuggingFace format) of the 1-bit Bonsai 27B 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 hybrid-attention kernels are currently in our forks of MLX, mlx-swift, 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 — a 14.2x memory reduction to 3.9 GB, interactive decoding on everyday laptops (44 tok/s on an M5 Pro), and the first 27B-class model that runs on a phone (11 tok/s on iPhone 17 Pro Max). This unpacked FP16 version is full-size (~54 GB) and does not provide any of those advantages.
For the optimized 1-bit release models (recommended):
For the quality-oriented variant:
Have the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo squ0sh/Bonsai-27B-unpacked-abliterated-uncensored ./model-folder