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

Property	Value
Architecture	Dense Qwen3.8-27B conditional-generation VLM (64 blocks: 48 GatedDeltaNet + 16 full attention)
JANG profile	JANG_AFFINE_TERNARY_2BIT
Text matrices	ternary {−s, 0, +s} in 2-bit slots, group size 128, exact
Weight basis	blockwise Hadamard rotation (block 1024, explicit signs), applied to activations at runtime
Vision linears	6-bit affine, group size 128
Norms and recurrent-state tensors	float32 passthrough (as in the source)
Weight shards	7.64 GiB
Context	262,144 tokens
Modalities	text, image, video
Audio	not supported

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.

Gate	Result
Logit parity vs Prism's reference loader	PASS — argmax agreement 1.0 at every position on 4 prompts, identical greedy continuations
Single-turn text, thinking off	PASS — Paris
Thinking on (reasoning_effort=medium)	PASS — closed think block, correct 391
Multi-turn	PASS — exact ORCHID-4729 recall and combination
Long context	PASS — buried fact recalled from a 10,655-token prompt
Image	PASS — red background with centered blue square; green circle plus exact OCR of overlaid text
Video	PASS — red frames followed by blue frames
Tool calling	PASS — get_weather call emitted and tool result folded into the final answer

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.