license: apache-2.0
base_model:

• prism-ml/Ternary-Bonsai-2-27B-gguf
• OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF
  tags:
• ninfer
• ternary
• bonsai
• heretic
• uncensored
• decensored
• speculative-decoding
• dflash2
• vision
  pipeline_tag: text-generation

Ternary Bonsai 2 27B — Uncensored Heretic (NInfer)

A native NInfer artifact (.ninfer) of the Heretic-decensored Ternary Bonsai 2 27B —
the uncensored variant, packaged for the consolidated NInfer engine
with DFlash2 speculative decoding, MTP, and the Qwen3.8-27B vision tower in a single file.

This fills a gap in the ecosystem: uncensored Bonsai 2 previously existed only in GGUF/MLX form,
which no NInfer build can load — and which cannot provide DFlash2 at all. This artifact gives the
NInfer audience the de-refused model at full NInfer speed.

Provenance

Upstream lineage: PrismML's ternary Bonsai 2 is derived from Qwen3.8-27B. Apache-2.0 throughout.

Contents

1,193 objects: ternary t2_g128_fp16 language projections, BF16/FP32 GDN controls, Q4/Q5
quantized vision tower (27 blocks + merger), MTP head, the full DFlash2 adapter stack
(feature projection, 5 draft layers, conv kernels, candidate-selector codebooks), and the
ternary proposal head. 9,520,051,456 bytes — byte-size identical to the official v3 artifact.

Requirements

• The consolidated NInfer line (iamwavecut/ninfer-3090 or a descendant build). The
  upstream ninfer releases do not decode t2_g128_fp16 weights.
• An NVIDIA GPU with roughly ≥20 GiB free for the configuration below (RTX 3090/4090/5090
  class; smaller cards can shrink --kv-capacity / context accordingly).

Example launch

ninfer-serve.exe \
  --model Ternary-Bonsai-2-27B-Heretic-ninfer.ninfer \
  --model-id bonsai2-27b-heretic \
  --spec dflash2 --draft-tokens 7 \
  --kv-dtype rk4v4-e8 --kv-capacity 1048576 --max-context 1048576 \
  --gdn-state-fp16 --max-concurrency 2 --cors \
  --port 11435

Vision variant: add --vision --vision-residency overlay --vision-max-merged 12288.

Measured (RTX 5090, sm_120a build, smoke tests — not a benchmark suite)

Caveats — read before benchmarking

• Draft acceptance is lower than stock. The DFlash2 adapter and proposal table were trained
  against the un-abliterated model's features. Speculation still roughly triples raw-decode
  throughput, but acceptance lands around ~20% instead of ~60%. If you measure it, that's why —
  not a corrupted artifact.
• Smoke-tested, not benchmarked. No perplexity or eval-suite numbers are claimed here.
• Retrieval degrades at the far end of 1M context — inherited from the base model; treat
  ~500–700K as the dependable window.
• No safety layer. This model is deliberately decensored and will answer requests the
  official model refuses. Deployment needs its own access controls and policies — nothing in
  the weights enforces them.

Integrity

SHA256SUMS contains the checksum for the artifact file. Verify before serving:

certutil -hashfile Ternary-Bonsai-2-27B-Heretic-ninfer.ninfer SHA256   # Windows
sha256sum Ternary-Bonsai-2-27B-Heretic-ninfer.ninfer                   # Linux

Credits

• PrismML — Ternary Bonsai 2 base model and ternary format
• OS-Software — Heretic decensoring baked onto the ternary lattice
• Qwen team — Qwen3.8-27B base, vision tower, tokenizer
• WaveCut / iamwavecut — the NInfer ternary engine line and conversion recipe
• ProCreations — MTP head and DFlash2 adapter weights