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

DreamFoundries/SuperQwen-AgentWorld-35B-A3B-abliterated-6bit

DreamFoundries 35B MoE 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/DreamFoundries%2FSuperQwen-AgentWorld-35B-A3B-abliterated-6bit"
Response includes
  • classification m1
  • files 14
  • hub_downloads_all_time 1,242
  • author_summary 12 models
  • readme_text full
Try next
GET/models?author=DreamFoundries
All 12 models by DreamFoundries
 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
1K
157 last 30d - stable
Likes
1
Model age
3mo ago
created 2026-07-02
Downloads over time
Now1.3K→from229↑463%
1765829891.4K229 on Jul 11.3K on Oct 11JulAugSepOct
Jul 1 → Oct 11 · 54 snapshots · spans 102 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.

Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated↓ 515 this lineage
DreamFoundries/SuperQwen-AgentWorld-35B-A3B-abliterated-6bit↓ 157

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5_moe mlx-lm quantized 6-bit base_model:Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated text-generation conversational base_model:quantized:Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated license:apache-2.0 region:us

Related

Other by DreamFoundries
SuperGemma-4-12b-abliterated-4bit 250 supergemma4-e4b-abliterated-6bit 225 supergemma4-e4b-abliterated-4bit 194 supergemma4-26b-abliterated-multimodal-8bit 190 SuperGemma-4-12b-abliterated-6bit 181
Same base model
MangoMikePower/SuperQwen-AgentWorld-35B-A3B-abliterated-Q5_0-GGUF 215 Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated-mlx-4bit 199 Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated-nvf4 175 Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated-gguf-4bit 152 DreamFoundries/SuperQwen-AgentWorld-35B-A3B-abliterated-8bit 75
Total size
26.2 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-25 19:20
Source huggingface.co/DreamFoundries/SuperQwen-AgentWorld-35B-A3B-abliterated-6bit ↗ Base model Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated →

Files by quantization

Auxiliary files 14 files 26.3 GB
model-00003-of-00006.safetensors 4.89 GB 03085ca7 download
model-00004-of-00006.safetensors 4.89 GB 718472ac download
model-00002-of-00006.safetensors 4.87 GB 81011192 download
model-00001-of-00006.safetensors 4.87 GB 52acfc49 download
model-00005-of-00006.safetensors 4.86 GB 365b4b1e download
model-00006-of-00006.safetensors 1.86 GB b8d52672 download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 183 KB d155a813 download
config.json 24.9 KB 5a75fe45 download
chat_template.jinja 13.3 KB d316dd1d download
README.md 1.59 KB 9f706dcb download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.24 KB 4ef302df download
generation_config.json 1.22 KB 9a1d2bbb download

README current version from Hugging Face

library_name: mlx
base_model: Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated
license: apache-2.0
pipeline_tag: text-generation
tags:

  • mlx
  • mlx-lm
  • quantized
  • 6-bit
  • base_model:Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated

SuperQwen-AgentWorld-35B-A3B-abliterated MLX 6-bit

This repository contains an MLX-LM conversion of Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated.

Conversion Details

  • Original model: Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated
  • Model family: SuperQwen AgentWorld
  • Source model type: qwen3_5_moe
  • Model size: 34,660,610,688 parameters
  • Quantization: MLX-LM affine quantization
  • Bits: 6-bit
  • Group size: 64
  • Local MLX folder size at upload time: 26.25 GiB
  • Local safetensors weight size at upload time: 26.23 GiB

Abliteration credit: the abliterated source model was published by Jiunsong. This repository only provides the MLX conversion and quantization.

Usage

mlx_lm.generate --model DreamFoundries/SuperQwen-AgentWorld-35B-A3B-abliterated-6bit --prompt "Hello" --max-tokens 64

Benchmarks

No comparative benchmarks have been run yet. The repository does not currently provide quality, speed, memory, or benchmark comparisons against the original weights or other quantizations.

License

This is a converted/quantized derivative of the original model. Please refer to the original model repository for the upstream license and usage terms: https://huggingface.co/Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated

README history 4 versions

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

  1. 2026-08-25Mueve Download MLXHub al final del documento2d170581.9 KB
    Loading...
  2. 2026-08-25Add Open in MLXHub / Download MLXHub badges068d2351.9 KB
    Loading...
  3. 2026-08-25Añade badges Open in MLXHub / Download MLXHubb18b6a42 KB
    Loading...
  4. 2026-07-02Upload MLX metadata80d9d891.6 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