dealignai/Bonsai-2-27B-1bit-CRACK-GGUF

text-generation model by dealignai

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Abliterated · No guardrails · PTQ10 dense-ternary 1.75 bpw · 5.9 GB · Runs on a laptop / single GPU · Vision-capable @dealignai Bonsai 2 27B — PrismML's ternary compression of Qwen3.8-27B — with the refusal circuitry surgically removed at the weight level while capability, vision, reasoning modes (off/low/xhigh), tool use, and multi-turn coherence are preserved. Full 27B-class hybrid Attention + SSM (GatedDeltaNet) architecture in a 5.9 GB 1bit GGUF. Proprietary weight-level abliteration by the dealignai research team. Byte-identical to the base ternary quant everywhere except a small set of tensors that carry the refusal circuit. Drop-in replacement for the ternary base at inference — same tokenizer, same chat template, same reasoning modes, same vision projector interface. Refusal graded on the tokens the model actually emits (content, or the reasoning trace when the model reasons past the token budget) via a tiered classifier: HARDREF / SOFTRED / HEDGE / REASONINGREFUSAL…

dealignai/Bonsai-2-27B-1bit-CRACK-GGUF on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-09-21T09:40:44.284Z

Inside the original model card — Document outline
  1. Bonsai 2 27B — 1bit CRACK · GGUF
  2. What is this
  3. Results
  4. HarmBench-320 — refuse rate (lower is better for uncensored eval), off mode, T=0
  5. Reasoning-mode compliance (n=60 base-confirmed refusers per mode)
  6. MMLU (n=2,280 = 40 questions × 57 subjects, next-token letter-logit)
  7. Additional direct refusal-removal check
  8. Serving
  9. Reasoning modes
  10. Preserved (byte-compatible with the base quant)
  11. Responsible use
  12. License & attribution

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

dealignai/Bonsai-2-27B-1bit-CRACK-GGUF is a text-generation model repository published by dealignai on Hugging Face. The source reports the llama.cpp library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
text-generation
Library
llama.cpp
Recent downloads (30 days)
12,894
Cumulative likes
61
Hugging Face trending score
53
Reported safetensors parameters
Not reported
Architecture
Not reported
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-09-17T23:59:09.000Z
Last modified
2026-09-18T07:50:53.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: prism-ml/Ternary-Bonsai-2-27B-gguf, Qwen/Qwen3.8-27B

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-09-21T06:36:47.722Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

Qwen/Qwen3-0.6B

openai-community/gpt2

trl-internal-testing/tiny-Qwen2ForCausalLM-2.5

Qwen/Qwen3-8B

unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

Qwen/Qwen2.5-7B-Instruct