Bonsai-2-27B-Ternary-JANG

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

Bonsai-2-27B-Ternary-JANG

JANG-affine bundle of prism-ml/Ternary-Bonsai-2-27B-mlx-2bit, Prism ML's ternary Bonsai 2 27B (built on Qwen3.8-27B). The language model is a lossless repack of Prism's ternary weights: every 2-bit code, scale and bias is carried over unchanged after validation. This is proper affine JANG storage, not JANGTQ, MXTQ, or a codebook sidecar format.

OsaurusAI · osaurus.ai · JANG source

Bundle

Embeddings, the untied language-model head, full-attention projections, GatedDeltaNet projections, and MLP matrices are ternary. Bonsai is dense: it has no routed experts or router tensors. The ternary codes decode to exactly the source {−scale, 0, +scale} groups.

The bundle contains the original tokenizer, tokenizer config, the Qwen3.8 chat template (thinking, reasoning_effort, tools), image and video processor configs, the Prism hadamard.json sidecar, source license and notice. EOS metadata is normalized to <|im_end|> (248046).

Runtime

The language model is stored in a Hadamard-rotated basis. Stock mlx_lm / mlx_vlm loaders return wrong output silently because they skip the activation transform. Use Osaurus or a vMLX build with JANG Hadamard support (osaurus.json names the minimum Osaurus version); the loader applies the transform from the bundle's declared contract and refuses to load if any sign vector is missing.

vmlx serve OsaurusAI/Bonsai-2-27B-Ternary-JANG --host 127.0.0.1 --port 8000

OpenAI-compatible chat requests support text, image_url, and video_url content parts, tool definitions, and chat_template_kwargs for enable_thinking and reasoning_effort (low, medium, xhigh; default xhigh).

Sampling defaults follow the Qwen3.8 card that Prism also recommends: thinking mode temperature 1.0, top_p 0.95, top_k 20; instruct mode temperature 0.7, top_p 0.80, top_k 20, presence_penalty 1.5.

Verification

Verified on 2026-09-17 through the vMLX Python server on an Apple M5 Max with 128 GB unified memory.

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

Quantization notes

• 402 language-model modules (embedding, 64 layers, untied head) are the source ternary codes, scales and biases, copied without re-quantization. There is no full-precision source for these weights, so AWQ, imatrix and GPTQ do not apply.
• 83 eligible vision linears use native 6-bit affine storage; blocks.N.mlp.linear_fc2 (input 4304) and the patch/position embeddings stay float16.
• 699 norms, GatedDeltaNet state projections, convolutions, biases and incompatible vision tensors pass through in their source precision.
• No tq_packed, tq_norms, mxtq_bits, or jangtq_runtime.safetensors artifacts are present.

License and attribution

Apache-2.0. See LICENSE and NOTICE.txt. This repository is a repacked conversion of the linked Prism ML Bonsai 2 checkpoint; the ternary weights are Prism ML's work.