← back to catalog · registered 2026-10-01 06:58

interimlabs/InterimLabs-Huihui-Qwen3.5-9B-abliterated-MLX-4bit

interimlabs 9B 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/interimlabs%2FInterimLabs-Huihui-Qwen3.5-9B-abliterated-MLX-4bit"
Response includes
  • classification unknown
  • files 11
  • benchmarks 11 entries
  • author_summary 6 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
788
Likes
0
Model age
7w ago
created 2026-10-01
Downloads over time
Now 1.3K → from 0 ↑ 0%
04639261.4K 0 on Oct 1 1.3K on Nov 22 OctNov
Oct 1 → Nov 22 · 53 snapshots · spans 52 days

Benchmarks

Benchmark Score Source
Entertainment 0.9 UGI
Hazardous 1.8 UGI
Natural Intelligence 14.88 UGI
Political lean -6.0% UGI
Sensitive-Info 11.44 UGI
SocPol 0.9 UGI
UGI 37.63 UGI
Willingness (10) 9 UGI
W10-Adherence 9 UGI
W10-Direct 9 UGI
Writing 29.12 UGI

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_text 4-bit qwen3.5 interimlabs abliterated text-generation conversational base_model:huihui-ai/Huihui-Qwen3.5-9B-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3.5-9B-abliterated license:apache-2.0

Related

Total size
4.69 GB
Files
11
Quantizations
1
Registered
2026-10-01 06:58
Last updated on HF
2026-10-08 16:59

Files by quantization

Auxiliary files 11 files 4.72 GB
model.safetensors 4.69 GB 511639bc download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
LICENSE 11.3 KB f938136e download
chat_template.jinja 7.57 KB a585dec8 download
manifest.json 2.10 KB 74293ce7 download
config.json 2.04 KB 7aebe526 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.21 KB 8cb2f1a3 download
tokenizer_config.json 1.11 KB a068e246 download
minstrel-provenance.json 500 B 2d17354f download

README current version from Hugging Face


license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3.5-9B-abliterated
library_name: mlx
pipeline_tag: text-generation
tags:

  • mlx
  • 4-bit
  • abliterated
  • minstrel

Interim Labs Huihui Qwen3.5-9B abliterated MLX 4-bit

This is a text-only, 4-bit affine/group-64 MLX derivative for Minstrel's optional Max · Unbound local language engine. It is based on the pinned vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-4bit snapshot 7b094180782d187b6f76242d085882914e6af181. The signed Minstrel manifest and provenance file are included for slot extended-abliterated-local, artifact version 0.1.0.

The reference abliterated upstream is huihui-ai/Huihui-Qwen3.5-9B-abliterated at 05b9e7c9b978ba29bdb8f50a49c30e4b91183339; the MLX converter does not establish the exact upstream revision it used. Huihui's 9B card does not document TRL fine-tuning. The Apache-2.0 license is copied from Qwen/Qwen3.5-9B at c202236235762e1c871ad0ccb60c8ee5ba337b9a. This package alone does not enable the model in Minstrel or establish writing-quality performance.

README history 3 versions

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

  1. 2026-10-08 Rebrand standalone Interim Labs release and link model series eca302a 4.8 KB
    Loading...
  2. 2026-10-01 Document signed Max Unbound MLX package 05cc9fd 1.2 KB
    Loading...
  3. 2026-10-01 initial commit 849235f 28 B
    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