← back to catalog · registered 2026-08-22 13:56

CallMcMargin/Huihui-Jan-nano-abliterated-mlx-bf16

CallMcMargin Qwen 4.0B 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/CallMcMargin%2FHuihui-Jan-nano-abliterated-mlx-bf16"
Response includes
  • classification m1
  • files 14
  • hub_downloads_all_time 173
  • author_summary 23 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 · lifetime
173
14 last 30d - cooling
Likes
0
Model age
11mo ago
created 2025-11-01
Downloads over time
Now179→from46↑289%
399014119246 on Nov 5, 2025179 on Oct 11Nov '25JanMarMayJulSep
Nov 5, 2025 → Oct 11 · 88 snapshots · spans 340 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
Languages
en
Tags
mlx safetensors qwen3 abliterated uncensored text-generation conversational en license:apache-2.0 region:us

Related

Total size
7.49 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-11-01 21:38

Files by quantization

Auxiliary files 14 files 7.51 GB
model-00001-of-00002.safetensors 4.96 GB 6487f148 download
model-00002-of-00002.safetensors 2.54 GB a879e5a8 download
tokenizer.json 10.9 MB 67cc0080 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 33.7 KB 767079ab download
tokenizer_config.json 5.38 KB 504f1ce6 download
chat_template.jinja 3.97 KB 0b04cc1e download
config.json 1.71 KB 0dcc7cb1 download
.gitattributes 1.53 KB 52373fe2 download
README.md 990 B 110efa95 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 127 B 8392b0f9 download

README current version from Hugging Face


license: apache-2.0
language:

  • en
    base_model: huihui-ai/Huihui-Jan-nano-abliterated
    pipeline_tag: text-generation
    library_name: mlx
    tags:
  • abliterated
  • uncensored
  • mlx

CallMcMargin/Huihui-Jan-nano-abliterated-mlx-bf16

This model CallMcMargin/Huihui-Jan-nano-abliterated-mlx-bf16 was
converted to MLX format from huihui-ai/Huihui-Jan-nano-abliterated
using mlx-lm version 0.28.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("CallMcMargin/Huihui-Jan-nano-abliterated-mlx-bf16")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

README history 1 version

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

  1. 2025-11-01Add files using upload-large-folder toold71a424990 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