Bonsai-27b-1bit-JANG

OsaurusAI/Bonsai-27b-1bit-JANG

Bonsai-27b-1bit-JANG is a image-text-to-text model from OsaurusAI. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.

<p align="center"<a href="https://osaurus.ai"<img src="./osaurus-x-banner.png" alt="OsaurusAI" width="100%"</a</p

Downloads · 30 days

399

14% of all-time downloads

All-time downloads

2.9K

Public

Parameters

1.7B

4.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors4.7 GB · 100%

Parameter types

How the weights are stored.

U321.2B · 67%

Try a prompt

Base models

prism-ml/Bonsai-27B-unpacked

Model card

From the Hugging Face model README

Bonsai-27b-1bit-JANG

Binary 1-bit JANG-affine conversion of prism-ml/Bonsai-27B-unpacked. This is proper affine JANG storage, not JANGTQ, MXTQ, or a codebook sidecar format.

OsaurusAI · osaurus.ai · JANG source

Bundle

Property	Value
Architecture	Dense Qwen3.5 conditional-generation VLM, 27B
JANG profile	`JANG_AFFINE_1BIT`
Text matrices	1-bit codes, group size 128
Vision linears	4-bit affine, group size 64
Norms and state tensors	float16 passthrough
Weight shards	4.346 GiB
Modalities	text, image, video
Audio	not supported

Embeddings, the untied language-model head, full-attention projections, GatedDeltaNet projections, and MLP matrices use the same discrete text profile. Bonsai is dense: it has no routed experts or router tensors. The packed one-bit codes are widened losslessly to native two-bit MLX slots in memory; scales and biases are unchanged.

The bundle contains the original tokenizer vocabulary, tokenizer config, Qwen chat template with thinking and tool support, image processor config, and video processor config. EOS metadata is normalized to <|im_end|> (248046). Source license and notice files are included.

Runtime

Use a vMLX Python build containing schema-2 discrete JANG-affine storage and mixed-precision vision support. Stock mlx_lm does not implement one-bit affine storage and does not honor this bundle's per-module mixed precision.

vmlx serve OsaurusAI/Bonsai-27b-1bit-JANG --host 127.0.0.1 --port 8000

OpenAI-compatible chat requests support text, image_url, and video_url content parts. The included chat template supports enable_thinking and tool definitions.

Verification

Verified on 2026-07-14 with vMLX Python on an Apple M5 Max with 128 GB unified memory.

Gate	Result
Single-turn text	PASS — coherent Paris answer
Multi-turn	PASS — exact `ORCHID-4729` recall through three turns
Hybrid cache	PASS — paged KV plus SSM companion cache hit
Image	PASS — identified red background and centered blue square
Video	PASS — identified red frames followed by blue frames

The conversion report is included as jang_affine_report.json; authoritative per-tensor storage metadata is in jang_config.json.

Quantization notes

498 discrete text matrices use the selected binary/ternary affine profile.
83 eligible vision linears use native 4-bit affine storage.
603 norms, state tensors, convolutions, biases, and incompatible vision tensors remain float16.
No tq_packed, tq_norms, mxtq_bits, or jangtq_runtime.safetensors artifacts are present.

License and attribution

Apache-2.0. See LICENSE, LICENSE.txt, and NOTICE.txt. This repository is a quantized conversion of the linked PrismML Bonsai source checkpoint.

Task: Image-Text-to-Text
Library: mlx
Type: qwen3_5
License: apache-2.0
Created: Jul 15, 2026
Updated: Jul 15, 2026