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

SC117/Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-GGUF

SC117 Qwen 35B GGUF MoE multimodal
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/SC117%2FQwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-GGUF"
Response includes
  • classification m-uncensored
  • files 10
  • hub_downloads_all_time 30,089
  • author_summary 18 models
  • readme_text full
Try next
GET/models?author=SC117
All 18 models by SC117
 GET/models?family=qwen&method=m-uncensored
Sibling qwen models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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 · lifetime
30K
2K last 30d - cooling
Likes
13
Model age
3mo ago
created 2026-07-08
Downloads over time
Now31.4K→from19.1K↑64%
18.5K23.2K28K32.7K19.1K on Jul 1531.4K on Oct 11JulAugSepOct
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.

Qwen/Qwen-AgentWorld-35B-A3B this lineage
SC117/Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-GGUF↓ 2,380

Metadata

License
apache-2.0
Languages
en zh
Quantizations
BF16
Tags
transformers gguf qwen3_5_moe qwen-agentworld world-model agentic-environment-simulation mtp abliterix apex quantization multimodal text-generation

Related

Other by SC117
Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF 907K Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF 106K Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-GGUF 71K Spark-X2.5-4B-abliterated-FIT-GGUF 24K occamy-1.0-abliterated-FIT-GGUF 18K
Same base model
Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated 515 huihui-ai/Huihui-Qwen-AgentWorld-35B-A3B-abliterated 338 Ichigec/SuperQwen-AgentWorld-35B-A3B-abliterated-APEX-I-Quality 64
Total size
141 GB
Files
10
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-10-03 10:24
Source huggingface.co/SC117/Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-GGUF ↗ Base model Qwen/Qwen-AgentWorld-35B-A3B ↗

Files by quantization

BF16 1 file 66.2 GB
Qwen-AgentWorld-35B-A3B-MTP-Uncensored-BF16.gguf 66.2 GB e4360a6d download
F16 1 file 858 MB
mmproj-F16.gguf 858 MB c8e70234 download
Auxiliary files 8 files 74.6 GB
Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-I-Balanced.gguf 24.1 GB 4e46871e download
Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-I-Quality.gguf 21.7 GB 1915652f download
Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-I-Compact.gguf 15.7 GB cdc94cd9 download
Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-I-Mini.gguf 12.8 GB 8542ee56 download
Qwen-AgentWorld-35B-A3B-MTP-Uncensored.imatrix.gguf 183 MB 4fea239b download
README.md 17.5 KB 67d4c4e1 download
README_zh.md 17.4 KB eee3e353 download
.gitattributes 2.07 KB cd3bf940 download

README current version from Hugging Face

library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
language:

  • en
  • zh
    tags:
  • qwen3_5_moe
  • qwen-agentworld
  • world-model
  • agentic-environment-simulation
  • mtp
  • abliterix
  • apex
  • quantization
  • gguf
  • multimodal
    base_model:
  • Qwen/Qwen-AgentWorld-35B-A3B
APEX-I MTP Abliterix GGUF

Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX

English | Chinese README

AgentWorld world model · Abliterix uncensored · native MTP injected · APEX-I GGUFs

Important Warning

Qwen-AgentWorld is designed as an agentic environment simulation / language world model. It is intended to simulate agent-environment interactions and predict environment states from actions and history. It is not recommended as a general daily assistant, coding model, or autonomous Agent backbone unless you specifically need this world-model behavior.

About This Release

This package contains GGUF releases of Qwen-AgentWorld-35B-A3B, a Qwen3.5 MoE world model for agentic environment simulation.

The model was modified with an Abliterix uncensored LoRA, stream-merged into safetensors, injected with one native MTP layer from a compatible Qwen3.5-35B-A3B MTP shard, converted to BF16 GGUF, and quantized into APEX-I tiers using a model-specific imatrix.

The release keeps the BF16 GGUF, imatrix, and mmproj-F16.gguf for reproducibility and multimodal llama.cpp use.

Model Details
Base modelQwen/Qwen-AgentWorld-35B-A3B
ArchitectureQwen3.5 MoE
Parameters35B total, around 3B active per token
Experts256 routed experts, 8 active per token
Context262,144 tokens
MTP1 injected MTP layer, 785 tensors
LicenseApache-2.0
Abliterix Build

The uncensored variant was produced with Abliterix. The selected search result was trial 54 out of 110.

KL divergence0.0163
Response length deviation0.04 std devs
Refusals21 / 100

The exported Abliterix LoRA was stream-merged into the full safetensors model before MTP injection and GGUF conversion.

MTP Extraction And Injection

The MTP layer was extracted from a compatible Qwen3.5-35B-A3B MTP shard and injected into the uncensored AgentWorld safetensors model.

Tensor prefixmtp.*
Tensor count785
Injected shardmodel-00022-of-00022.safetensors
BenchLocal Results
ModelTCBFHACeilingPracticalRetry
Original, thinking100878188.587.51
Uncensored + MTP, thinking93877985.681.64
Uncensored + MTP, no thinking83836375.075.00
Qwen3.6-35B thinking baseline97888589.581.58

Thinking mode is strongly recommended for this model family.

Usage

llama.cpp server

hf download SC117/Qwen-AgentWorld-35B-A3B-MTP-Uncensored-GGUF --include "*.gguf" --local-dir ./models/qwen-agentworld-mtp-uncensored ./llama-server -m ./models/qwen-agentworld-mtp-uncensored/Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-I-Compact.gguf -ngl 99 -c 131072

vision + text

./llama-server -m ./models/qwen-agentworld-mtp-uncensored/Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-I-Compact.gguf --mmproj ./models/qwen-agentworld-mtp-uncensored/mmproj-F16.gguf -ngl 99 -c 131072

APEX Quantization Tiers
FileSizeProfileBest For
*-APEX-I-Balanced.gguf24.14 GBI-BalancedHighest-retention all-rounder
*-APEX-I-Quality.gguf21.68 GBI-QualityQuality-focused, IQ4_XS middle experts
*-APEX-I-Compact.gguf15.75 GBI-CompactRecommended quality/size ratio
*-APEX-I-Mini.gguf12.80 GBI-MiniSmallest practical tier

The model-specific imatrix was generated from cleaned AgentWorld calibration text: PPL = 4.5880 +/- 0.01173.

Links

Citation

@misc{qwen-agentworld-2026,
  title = {Qwen-AgentWorld: Language World Models for General Agents},
  author = {Qwen Team},
  year = {2026},
  url = {https://github.com/QwenLM/Qwen-AgentWorld}
}

README history 4 versions

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

  1. 2026-10-03Add optional Ko-fi support bannerb0dd31617.9 KB
    Loading...
  2. 2026-07-08Update README.md5ce97ea17.5 KB
    Loading...
  3. 2026-07-08Update README.md8a9293c17.5 KB
    Loading...
  4. 2026-07-08Add files using upload-large-folder tooleff383317.4 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