← back to catalog · registered 2026-11-18 17:04

grokked-it/Qwen3.8-27B-pi-abliterated-oQ6e-fp16-mtp

grokked-it 27B multimodal second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/grokked-it%2FQwen3.8-27B-pi-abliterated-oQ6e-fp16-mtp"
Response includes
  • classification m1
  • files 18
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
116
Likes
0
Model age
3d ago
created 2026-11-18
Downloads over time
Now 116 → from 0 ↑ 0%
04385128 0 on Nov 18 116 on Nov 22 Nov
Nov 18 → Nov 22 · 5 snapshots · spans 4 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5 omlx oq oQ6e quantized imatrix mtp pi agents abliterated

Related

Total size
23.1 GB
Files
18
Quantizations
1
Registered
2026-11-18 17:04
Last updated on HF
2026-11-18 16:23

Files by quantization

Auxiliary files 18 files 23.1 GB
model-00001-of-00005.safetensors 4.98 GB 8e9d0cc6 download
model-00003-of-00005.safetensors 4.70 GB dcb7008f download
model-00004-of-00005.safetensors 4.69 GB 645037cc download
model-00002-of-00005.safetensors 4.67 GB 8c7b2af2 download
model-00005-of-00005.safetensors 4.04 GB 80776561 download
tokenizer.json 19.1 MB a5cd9732 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 207 KB dc554134 download
oq_imatrix_report.json 32.5 KB 0b2ad8a9 download
config.json 14.8 KB 73b6dade download
LICENSE 11.3 KB f938136e download
chat_template.jinja 8.79 KB 9bd39df8 download
README.md 3.06 KB b603b011 download
tokenizer_config.json 2.43 KB c23583c5 download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 390 B 2ea84a43 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face


library_name: mlx
license: apache-2.0
base_model:

  • huihui-ai/Huihui-Qwen3.8-27B-abliterated
  • harness-hub/Qwen3.8-27B-pi-adapted
    pipeline_tag: image-text-to-text
    tags:
  • mlx
  • omlx
  • oq
  • oQ6e
  • quantized
  • imatrix
  • qwen3_5
  • mtp
  • pi
  • agents
  • abliterated
  • uncensored

Qwen3.8-27B-pi-abliterated-oQ6e-fp16-mtp

huihui-ai/Huihui-Qwen3.8-27B-abliterated with the harness-hub/Qwen3.8-27B-pi-adapted LoRA adapter merged in, quantized for Apple Silicon with oMLX oQ6e. The adapter was trained with reinforcement learning for the pi coding agent; see its card for the method and the benchmark results, which were measured on the unquantized, non-abliterated model.

The non-abliterated sibling is grokked-it/Qwen3.8-27B-pi-oQ6e-fp16-mtp.

The checkpoint holds the language model, the vision encoder and the multi-token prediction (MTP) head.

How it was made

  1. Merge. The adapter (LoRA, rank 32, alpha 64, 256 linear layers of the language model) was merged into the abliterated BF16 weights: W' = W + 2 · B · A, computed in float32 and stored back in BF16, one shard at a time. The adapter was trained on the original Qwen weights, not on the abliterated ones. The vision encoder and the MTP head are the abliterated repository's, which its card says are unmodified from the base model.
  2. Quantize. oMLX 0.8.0, oQ level 6, enhanced (e): mixed precision by layer sensitivity, importance matrix on the oqe_code_multilingual calibration set (128 samples of 512 tokens, adaptive), code refinement. Scales, biases and unquantized tensors in FP16, MTP head preserved.
Base bits 6-bit affine, group size 64
Tensors raised to 8 bits 44
Size 24.8 GB
Estimated effective bits per weight 6.87 (oMLX estimate before the run)

Tokenizer and chat template come from the adapter repository.

Usage

Load it in oMLX, or with any MLX loader that supports the Qwen3.5 architecture.

The adapter's authors recommend thinking off ("chat_template_kwargs": {"enable_thinking": false}) and report their results at temperature 0.8, top-p 1.0. Tool calls use the base model's format.

This model has its refusal behaviour removed and will comply with requests the base model declines. You are responsible for how you use it.

Limits

  • No benchmark was run on this checkpoint. It passed only a smoke test in oMLX: one code completion, one tool call, and two prompts that the non-abliterated sibling refused and this model answered.
  • Two prompts do not measure how complete the abliteration is after the merge.
  • The MTP head was trained against the original backbone, not the adapted or abliterated one.
  • The merge rounds to BF16 before quantization, as the adapter card's own merge recipe does.

License

Apache-2.0, following the base model, the abliterated weights and the adapter. See LICENSE.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-18 Add oQ6e quantization of the pi adapter merged on abliterated Qwen3.8-27B 88f6089 3.1 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration