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

usermma/NEXUS-Coder-Abliterated-mlx-5Bit

usermma Qwen 1.5B 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/usermma%2FNEXUS-Coder-Abliterated-mlx-5Bit"
Response includes
  • classification m1
  • files 9
  • hub_downloads_all_time 54
  • author_summary 77 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
54
17 last 30d - stable
Likes
0
Model age
3mo ago
created 2026-07-11
Downloads over time
Now60→from23↑161%
2135506423 on Jul 1560 on Oct 1160 on Oct 7JulAugSepOct
Jul 15 → Oct 11 · 53 snapshots · spans 88 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

Tags
mlx safetensors qwen2 obliteratus abliteration uncensored obliterate mlx-my-repo en base_model:usermma/NEXUS-Coder-Abliterated base_model:quantized:usermma/NEXUS-Coder-Abliterated 5-bit

Related

Total size
1012 MB
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-11 12:55

Files by quantization

Auxiliary files 9 files 1023 MB
model.safetensors 1012 MB eeb19c87 download
tokenizer.json 10.9 MB bd5948af download
model.safetensors.index.json 50.4 KB 16d03b01 download
chat_template.jinja 2.45 KB bdf7919a download
config.json 1.81 KB 1f2dfb5c download
.gitattributes 1.53 KB 52373fe2 download
README.md 967 B 93f93c3a download
tokenizer_config.json 572 B b58166ce download
generation_config.json 264 B a964fccc download

README current version from Hugging Face


language: en
tags:

  • obliteratus
  • abliteration
  • uncensored
  • obliterate
  • mlx
  • mlx-my-repo
    base_model: usermma/NEXUS-Coder-Abliterated

usermma/NEXUS-Coder-Abliterated-mlx-5Bit

The Model usermma/NEXUS-Coder-Abliterated-mlx-5Bit was converted to MLX format from usermma/NEXUS-Coder-Abliterated using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("usermma/NEXUS-Coder-Abliterated-mlx-5Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, 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. 2026-07-11Upload folder using huggingface_hubf0e1e6d967 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