alt.freeweights.text / Bonsai-27B-unpacked

From: prism-ml <huggingface.co/prism-ml>Newsgroups: alt.freeweights.textSubject:

Bonsai-27B-unpacked

Date: 2026-11-15Commit: d619b27Signed: 2DC28CC7B26A283B ✓

Model with 27.4B parameters. Safetensors weights, 54.7 GB in all. Published by prism-ml under Apache-2.0.

27.4B params54.7GBBonsai-27B-unpackedsafetensorspermissive

FactsParams27.4BSize54.7 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive

$ fw get prism-ml/Bonsai-27B-unpacked
# manifest sha256 aa0973ac8f12… · 54.7 GB · 29 files
$ fw verify ./Bonsai-27B-unpacked prism-ml/Bonsai-27B-unpacked

From sourceHosted (signed)prism-ml/Bonsai-27B-unpackedLast check: 2026-11-15 02:42 UTC

Run at home Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Run8 Fine-tune7 Convert8 Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

Transformers LocalAI tinygrad Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Overview

Size: 54.7 GB
Weights: 54.7 GB (safetensors)
Parameters: 27.4B
Formats: safetensors
Task: not tagged
License: Apache-2.0 (permissive)
Files: 29, each with a sha256
Publisher: prism-ml
Added: 2026-11-15
Section: alt.freeweights.text

Lineage

Original release from the publisher.

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 02:42 UTC	passed

Model card

From the publisher at commit d619b27. Shown as plain text with links; images open at the publisher.

1-bit Bonsai 27B — Unpacked FP16 Safetensors#

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):

Bonsai-27B-mlx-1bit — 1-bit MLX for Apple Silicon (Mac, iPhone, iPad)
1-bit GGUF (Q1_0_g128) for llama.cpp (CUDA, Metal, CPU)

For the quality-oriented variant:

Ternary-Bonsai-27B-mlx-2bit — Ternary Bonsai 27B (~7.2 GB, 95% of FP16) for laptops and GPUs

Files

29 files · 54.7 GBWeights 54.7 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 29 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE	11.3 KB	50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
LICENSE.txt	10.2 KB	69849221bfb90053de2134ef5e6d540287b4b98062326492f1f96f5da685524b
NOTICE.txt	411 B	cef33f95425f9802de78b7b22db0faca84d2216661432a9afcf9620949c21f7e
README.md	1.56 KB	3358bc4b0bee5cb464f3fd1dd760f470a260b27c550c90c2976addb7978951bf
chat_template.jinja	7.76 KB	e84f32a23fdda27689f868aa4a1a5621f41133e51a48d7f3efcbea2839574259
config.json	4.31 KB	69db4eb7196bc8190813231b3018ca05d8c2e3abc7b1af19d55c157af44a9d9c
configuration.json	51 B	2d4464e2ead06bc9bc718c781309ad1e7baded626d66e8dcdc8b469ba185faf0
generation_config.json	202 B	e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e
merges.txt	3.35 MB	a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
model-00001-of-00012.safetensors	2.54 GB	306d4560b3d0453d8d957f3372966076b40539144ecce0f2ed5407383c97bed6
model-00002-of-00012.safetensors	4.84 GB	e549d3f5832136ee90188ade6e4f4c36c37214848a5d16948bd8e304a0626c88
model-00003-of-00012.safetensors	4.97 GB	93365de201fa5bc29cfca82bb05e264d90c63805ba286a960193113e6ad25c84
model-00004-of-00012.safetensors	4.93 GB	6a06aea936dfc4beee47e19ef3cfdc8ce7535ab2330821298069f4bdc8f5d531
model-00005-of-00012.safetensors	4.97 GB	d6c97cdab86082fe17eed56f05cb3c11fc46754f0fe160e310f4238b792a9d6e
model-00006-of-00012.safetensors	4.91 GB	ed9ad04586a3340db3aad96ab968dcd3fad661dc4b9698ab3d2084d71c3eabb7
model-00007-of-00012.safetensors	4.97 GB	ca978c38a32f4f272e595dca44ef2e668e8c686e559b83cafbe1c30b09dbd53d
model-00008-of-00012.safetensors	4.93 GB	a593389b97222794dbfbfce4e73a61c8a0b56347bfa3dac7767f63148cdd4cab
model-00009-of-00012.safetensors	4.97 GB	c40d04ca503d94418be27249833a86522d511d0d74e0daaa101dbde2ddbdce81
model-00010-of-00012.safetensors	4.93 GB	dac3e5edc9509f972174fe0f167b0b8f53e47656f4f4125fb1297ecce7c0955a
model-00011-of-00012.safetensors	4.91 GB	f6312a8711ed05b882d510b8884b2da1c2f5a093908c41beb142de39705266ad
model-00012-of-00012.safetensors	2.84 GB	dd0a9b56ce2455f596c4f26afe28fc2bc5a50655f9c58e702ffb1cd43a6d1e1a
model.safetensors.index.json	111 KB	25647faf465e6387795de0583295e5b78229a3791c8f747fbbda0707cde799c2
preprocessor_config.json	390 B	27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
processor_config.json	44 B	18c83d74295314cbc86099e83ad945d300cca54270d3ecc9f4ff8fe8cb89d911
tokenizer.json	12.8 MB	5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
tokenizer_config.json	16.7 KB	5186f0defcd7f232382c7f0aebcd2252d073bb921ab240e407b7ae8745d2b29b
video_preprocessor_config.json	385 B	7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json	6.72 MB	ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
d619b27283 pinned now	2026-11-15 02:42 UTC	29 files · 54.7 GB

Use it

$ fw get prism-ml/Bonsai-27B-unpacked
# manifest sha256 aa0973ac8f12… · 54.7 GB · 29 files
$ fw verify ./Bonsai-27B-unpacked prism-ml/Bonsai-27B-unpacked

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/prism-ml/Bonsai-27B-unpacked.json --dir ./Bonsai-27B-unpacked
$ python3 fw.py verify ./Bonsai-27B-unpacked ./prism-ml__Bonsai-27B-unpacked.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download prism-ml/Bonsai-27B-unpacked --revision d619b27283ac02b4199ced97a89419529dc0bfac --local-dir ./Bonsai-27B-unpacked

Run at home

License

Name: Apache License 2.0
Id: Apache-2.0
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: License as declared by the publisher. No person read it. 2026-11-15
Text in: LICENSE
Text sha256: 50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
Terms gate: No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: prism-ml <huggingface.co/prism-ml>Newsgroups: alt.freeweights.textSubject: Bonsai-27B-unpackedDate: 2026-11-15Commit: d619b27Signed: 2DC28CC7B26A283B ✓

Upstream: prism-ml/Bonsai-27B-unpacked
Pinned commit: d619b27283ac02b4199ced97a89419529dc0bfac
Manifest: Bonsai-27B-unpacked.json · .minisig
Manifest sha256: aa0973ac8f12f817877271adf7a7ed493ba96c4f38d4b6c5282f601dd468419d
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 02:42 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/prism-ml/Bonsai-27B-unpacked.json
$ curl -O https://freeweights.allternit.com/manifests/prism-ml/Bonsai-27B-unpacked.json.minisig
$ minisign -Vm Bonsai-27B-unpacked.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

1 model in the catalog name this one as their parent.

Quantizations: 1

Quantizations 1

lmstudio-community/Bonsai-27B-GGUF4.73 GB

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download prism-ml/Bonsai-27B-unpacked

Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest

minisign, key 2DC28CC7B26A283B. Bonsai-27B-unpacked.json. Provenance. Takedown history: none.

Source

huggingface.co/prism-ml/Bonsai-27B-unpacked

Variants

1 quantized or adapter build of Bonsai-27B-unpacked. Each has its own license check and page.

SubjectSizeParamsLicenseDate

Bonsai-27B-GGUFHosted (signed) From: lmstudio-community in alt.freeweights.text4.73 GB—Permissive2026-11-15

Related models

All of alt.freeweights.text →

From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B