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

AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX

AITRADER Qwen 9.0B
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/AITRADER%2FJackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX"
Response includes
  • classification m1
  • files 10
  • hub_downloads_all_time 3,125
  • author_summary 30 models
  • readme_text full
Try next
GET/models?author=AITRADER
All 30 models by AITRADER
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
3K
263 last 30d - cooling
Likes
3
Model age
7mo ago
created 2026-03-08
Downloads over time
Now3.3K→from561↑479%
4271.5K2.5K3.5K561 on Mar 113.3K on Oct 11MarAprMayJunJulAugSepOct
Mar 11 → Oct 11 · 70 snapshots · spans 214 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.

Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled this lineage
AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX↓ 263

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5 abliterated uncensored qwen3.5 reasoning claude-distilled mxfp8 quantized text-generation conversational

Related

Other by AITRADER
Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-mlx-mxfp8 298 Huihui-Qwen3-Coder-Next-abliterated-mlx-8Bit 251 gemma-4-31B-Claude-Opus-Distill-abliterated-mlx-mxfp8 211 Qwen2.5-VL-32B-Instruct-abliterated-mlx-fp16 203 Huihui-Qwen3-Coder-Next-abliterated-mlx-4Bit 192
Same base model
AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-fp16-MLX 96 Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled 34
Total size
9.45 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-13 21:43
Source huggingface.co/AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX ↗ Base model Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled ↗

Files by quantization

Auxiliary files 10 files 9.47 GB
model-00001-of-00002.safetensors 4.98 GB edfb6a76 download
model-00002-of-00002.safetensors 4.47 GB 7e76dc2c download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 95.6 KB 6fe202cb download
chat_template.jinja 3.95 KB 609532bf download
config.json 3.56 KB 8bf31ddb download
README.md 1.69 KB b2af4233 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.17 KB 594fd860 download
preprocessor_config.json 336 B 4ae180b4 download

README current version from Hugging Face

base_model: Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
language: en
pipeline_tag: text-generation
library_name: mlx
tags:

  • mlx
  • abliterated
  • uncensored
  • qwen3.5
  • reasoning
  • claude-distilled
  • mxfp8
  • quantized
    license: apache-2.0

Jackrong Qwen3.5-9B Claude Reasoning - Abliterated (MXFP8 MLX)

This is an abliterated (uncensored), MXFP8 quantized version of Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled, converted to MLX format for Apple Silicon.

What is this model?

The base model is Qwen3.5-9B fine-tuned on Claude 4.6 Opus reasoning data using Unsloth/LoRA. This version is abliterated (safety refusals removed) and quantized to MXFP8 for reduced memory usage (~8.6 GB vs ~16.6 GB bf16).

Abliteration Details

  • Method: lukey03 (1 direction, norm-preserving, 3 refinement passes)
  • Post-processing: LoRA compliance fine-tuning (rank=64, 80 iterations)
  • Quantization: MXFP8 (8.25 bits per weight)
  • Format: MLX (Apple Silicon native)
  • Tool: OBLITERATUS

Usage

pip install mlx-lm

mlx_lm.generate --model AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX --prompt "Explain quantum computing"

Full Precision Version

The bf16 version is available at: AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-fp16-MLX

Disclaimer

This model is provided for research purposes. Users are responsible for ensuring their use complies with applicable laws and regulations.

README history 1 version

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

  1. 2026-03-08Upload folder using huggingface_hub6e3c1ad1.7 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.

Get the app Browse the catalog
Open in Abliteration